Happy New Year! Hard to believe this is my last blog of 2023. I’ve been writing about using Artificial Intelligence in family history research for the past few weeks. I hope it has been helpful and taken the fear out of the tech. Whenever I’ve talked about it with my personal FAN Club, I get the same reaction which is either a sign of the cross and the question, Haven’t you seen the terminator movie? to Oh, I want to learn how to do that. Absolutely no reactions in between!
Which I think is quite interesting because I’m a middle of the roader. I love the time saving aspect and the assistance in handling large amounts of data to analyze but I also am very cognizant that this tech is still in it’s infancy, makes mistakes (like people do), and due to lack of transparency from the companies involved, we have no idea what training information was used. So, it could have been an item that was under copywrite, it could have been biased information, or it could have been false information.
That said, I still think it can be useful. I really miss an early Google AI attempt called Picasa. I had saved all of my family photos there and it could identify family members that were infants I could not. I have two sets of twin cousins and in some of the photos I can’t tell them apart. Picasa was able to separate them out individually.
Today, AI can also create pictures. I haven’t tried to input photos from say, 1890, and ask it to take the person in the photo and create a new picture in 1820 period clothes but I suspect that can be done. Sounds interesting and want to get started?
Through ChatGPT I use Dall-E. It has become one in the same since November. Before that, Dall-E was Beta but now they are joined. Here’s how to use AI to get a picture.
In the chat box, ask to “Create a picture or photo of” whatever. You can be specific or not.
When you get a response you might want to edit the picture. You can have the AI do that by specifically stating what you want altered. In the photo above, I asked to update the first image with the word “2024” added. I never told it where to add but perhaps you wanted it front and center. You can then tell it to add a calendar showing the month of January and the year 2024 displayed.
I will be one of seven professional genealogists giving a lecture at an upcoming genealogical conference later in 2024. I will be using AI to create some of the slide pics. For some slides, I had an idea but for others, I let AI create for me with only the slide title as the instruction.
Ethically, I believe that I need to credit AI for the pictures, just as I would source any photo that I use.
I hope you are enjoying the holidays with family and friends. I look forward to 2024 and providing you with more heartfelt and informative blogs. All the best to you and yours!
Previously I blogged about using Artificial Intelligence (AI) to create narratives of your ancestor’s lives. Today, I’m going to show you how you can take those online classes you are attending and make concise notes from the chat box.
Why the chat box you may think? Because the chat box often contains important information that participants have thought about the subject to add – new questions to ask the speaker – and resources and links that someone attending found useful.
Here’s the how to turn your chat box chatter into useful info:
At the end of the session, either highlight the enter chat box conversation and copy (ctr c) to a Word document (ctr v). Save as a pdf.
Upload to ChatGPT, Claude, or Bard. (Try more than one to see the results and which you prefer).
Provide a prompt – “You are a professional genealogist and expert writer. Please create an executive summary from the information provided. List attendees, key topics discussed, key questions raised, and notable moment.
You can also do this from YouTube videos for the class itself if you don’t have time to view it. Here’s a how to get a copy of the transcript. Then, follow the three steps noted above. You can tell your AI helper to make a title of the video you watched, add the date, and add the speaker’s name, too. Personally, I’d save the results to my Dropbox as I keep syllabi there to refer to in the future, if needed.
Like last week, my answer is a strong maybe! I’ve been researching my John Duer, Patriot, and his relationship to his purported son, Thomas for YEARS! I have so much indirect evidence and one piece that does state Thomas was the son of John but it is in a collection made beginning in 1865 that doesn’t provide the source. Of course!
So, I turned to AI to get its take on the problem.
Before I tell you the result, I want to share with you how to take data and create an Excel table using AI. It’s so super simple and saves a lot of time. WARNING: Like with all new tech, you much check for accuracy. Don’t assume it is 100% correct. Even with the time taken for that, it will be a time saver in the long run.
Create a prompt to “extract structured data from…” whatever you uploaded. From the class I took, it was suggested we add “prioritize fidelity to the information below; dry recitation, avoid editorialization. Prioritize sentence-by-sentence from beginning to end. Extract from the (uploaded item) this structured data… (list whatever info you want). Display your response in the form of a CSV file. The response should have the header row: (titles you want – could be) “Person’s Names”, “Relationships Noted”, “Evidence of the Relationship” (or whatever you deem important). Enclose all cells or fields in quotation marks, omit, ignore, and avoid commas and other punctuation in the original text in your response in an attempt to keep the CSV error-free. Display your response in a code window for easy copy-and-paste.
Upload your item as a .pdf file.
A black box will display with the text in white letters. You can ctr c and ctr v into Notepad (you can find notepad by typing Notepad or Text in your computer search bar). Or, you can click on the upper right screen on ChatGPT and share, then copy code.
Open the file in Excel and clean it up, if necessary.
Then I opened a new ChatGPT message and gave the following prompt: Today you and I are an expert genealogist and writer. Your goal is to generate true and accurate reports. Find below the contents of a CSV file created from my research on the relationship of John and Thomas Duer. Transform the structured data into a narrative report; dry recitation, no editorialization, please.
This is what I received:
John Duer was born on January 19, 1748, in Cranbury, Middlesex, New Jersey. Various sources, including family data collections and genealogical websites, document this event. The death of John’s mother, Mary Ann Hollingshead Duer, occurred in 1751 in Newton, Sussex, New Jersey, although specific source documentation is absent beyond public family trees.
In 1773, John married Susannah Miller in Sussex, New Jersey. Their marriage is recorded in the Family Data Collection and referenced in genealogical records from Youngstown and Mahoning County, Ohio. The couple had several children, the first of which was Esther Duer Hopkins, born in Monmouth, New Jersey, in 1774. However, there is a discrepancy in her birth location, as other sources suggest Sussex County, New Jersey, as her birthplace.
John’s military service is confused with that of a cousin who served in the Pennsylvania militia. Despite this error, records from Ohio acknowledge John Duer’s service, including listings in the official roster of American Revolution soldiers buried in Ohio.
Thomas Duer, John’s son, was born in 1775 in Sussex, New Jersey, with multiple sources confirming this, though his gravestone lacks specific dates. Jonathan Duer followed on November 11, 1777, also in Sussex, with his life documented through family data collections and census records.
Joseph Duer’s birth in 1779 is only supported by public family trees, lacking concrete source documentation. In 1780, Mary Duer Hazen, another of John’s daughters, was born in Sussex. Her lineage is established through the DAR lineage book and a family history published in 1947.
John Duer was a church member at the First Baptist Church of Wantage, Sussex, New Jersey, in 1783, with historical records from the Sussex County Historical Society likely supporting this fact. His military service is further documented in DAR and New Jersey Revolutionary War records, as well as in family genealogical files.
In the following years, John resided in Newton, Sussex, New Jersey, where he is listed as a vestryman in a history of Christ Church, and in Hanover Township, Morris County, New Jersey, as indicated by tax records. He also engaged in land transactions, including purchasing land that would later become part of West Virginia, and in 1797, he was a resident of Mansfield Township, Sussex, New Jersey, acting as a bondsman.
John’s life from 1798 to 1829 included various land dealings, military service records, family events such as the deaths of his sister Anna Duer Hull and his son Thomas Duer, and his own death on April 3, 1831, in Jackson Township, Trumbull, Ohio. His will was probated in March 1832, and his estate included guardianship arrangements for his grandchildren.
The narrative concludes with references to Thomas Duer’s estate papers, tax records, and land transactions that involved John Duer and his son Thomas. The document also notes a DNA connection to the family through Elizabeth Suriner and references to historical maps and newspaper articles related to the Duer family in Hubbard, Trumbull, Ohio.
Interesting, huh?! Nowhere in the csv data did it say that Thomas was John’s son. My headings were Date, Event, Place, Source, Name. Would this be accepted by a lineage society? Definitely not but it was an unbiased analysis of the indirect evidence. I did provide in the prompt to look for a relationship of John and Thomas Duer but did not state it was father-son.
I’d love to hear what you find in using AI to establish relationship.
Prompt Chaining in Artificial Intelligence (AI) to me just means taking baby steps to get to your desired end product. It’s like wanting your three year old to follow four directions but that’s too much so you give them three and then add the fourth.
What I wanted to do was use AI to extract (pull out) key parts of newspaper articles about my grandfather Edwin Anton Leininger to do the following:
Create an executive summary of the articles
List the FAN club noted in the articles
Determine the FAN Club relationship to my grandfather
List locations from the articles
Note dates from the articles
Create a narrative based on the relationships and key details from the articles
Think about how long this would take you to do. It took ChatGPT less than 5 minutes.
Was it entirely accurate? Nope, and here’s where it got creepy.
My first step was to select six newspaper articles over the time period my grandfather lived and from various locations. Chat GPT can only handle about four newspaper articles at a time so I uploaded those first sets (one from 1918 where he was collecting money for the war effort for YMCA in Ohio, a 1970 article about the historic dairy farm he once ran in Indiana, a 1950 story about a calf who had escaped from the farm, a 1940 article about him buying the farm). I didn’t upload them in chronological order. I then asked for a summary of the four articles. What I received was all correct; each article had the heading taken from the article and key points bulleted.
Next I uploaded his obituary and a photo from 1944 with a short heading of his job with the railroads. I asked AI to add the two latest articles to the summary.
But AI has a short memory so what I received was the summary for just the two last articles. I wrote a new prompt asking for a creation of an executive summary for the articles combined.
AI did as I asked so I then requested to extract the names and provide relationships. I also asked to list locations from the articles. Here’s where it got weird!
First, there were errors with names. I quickly figured out Mrs. Troncale was misread and should have been Tronolone. AI didn’t figure out that my grandfather was listed by different names – Edwin A., E.A., and Ed. AI thought these were all separate individuals. It also placed locations with names; technically this is correct as the name of a dairy is a name and I hadn’t given a clear direction for geographic names only.
I informed AI of the mistakes/corrections and received a new list. I then asked AI to substitute first names for women who had “Mrs.” only. That was done correctly.
In reviewing the last list three names appeared that were related to my grandfather but I didn’t recall those being in the articles. I went back and read all six articles. Nope, none of these names appeared. Where did this come from?
I asked Chat GPT to let me know where the names were found. I received an apology and a name removal.
The creepy part here is that the names were correctly related to my grandfather. One was his sister, another was his mother-in-law, and the third was his grandfather. How in the world did AI happen to select the right first and last names that were related to him?
We know AI is not 100% accurate but to select three people, all with different last names, and tie them to the extraction when they weren’t listed in simply weird. So I asked (response above). The response doesn’t provide the answer. I don’t believe AI is psychic and the information came from somewhere. I suspect that information is in fact being pulled externally and perhaps not now, but had been in training.
The end product, a summary of the six newspaper articles taken from throughout my grandfather’s life, was correct. Here it is:
A Legacy Through Time Edwin Leininger, often referred to by his acquaintances as Ed or E.A. Leininger, led a life characterized by commitment and dedication. Born in Mercer County, Ohio, he later made Fort Wayne his home for nine years. Professionally, Edwin was recognized for his unwavering commitment to the Pennsylvania Railroad, where he diligently worked as a car inspector. Later in life, he became an indispensable figure at the Hobart post office, where he was affectionately referred to as “the man with the muscles.” For years, he efficiently managed both outgoing and incoming mail, handling approximately 9,500 pieces of outgoing mail and 2,000 pieces of incoming mail daily. On the personal front, Edwin’s life was richly woven with familial bonds. In his earlier years, he was married to Lola Leininger. Together, they embraced the joys of parenthood with the birth of their children: a son, Guy Leininger; a daughter, Mrs. Bonita Cook; and another daughter who later became Mrs. Ted Tronolone. Later in life, Edwin’s heart found companionship again with Gladys Leininger. Through this union, Edwin warmly welcomed Gladys’ three sons, Duane, Donald, and Capt. Robert Landfair, as his step-sons. Edwin’s family circle extended further with his brothers, Sam and Lew Leininger, and a sister, Bertha, who later became Bertha Pifer. The bond of the Leiningers remained strong, binding them together through the tapestry of time. In 1976, Edwin’s journey on Earth reached its sunset in Fort Wayne. Yet, his legacy—reflected in his professional dedication, familial bonds, and community impact—lives on.
NOTE: This blog was posted on 25 Nov 2023 on the Empowering Genealogists with Artificial Intelligence Facebook group. Since my blog two weeks ago on using AI to write a narrative, I’ve been getting a lot of questions and comments. I’ve been told that AI doesn’t work with some sites; I have found that to be not true. I have also found a temporary work around for footnote/endnote citations that look more like what genealogists use – simply provide this prompt: Please write all footnotes in Chicago format style. You will have to go back and fill in some info, like the enumeration district for censuses, but it will be closer to what we are used to seeing.
I was interested in seeing how a narrative summary with endnotes from various sources that had similar data would be written.
I used the same prompt: You are a professional genealogist and expert writer. Please write a narrative summary with endnotes from the attached file. (AI seems to place all sources at the end, whether you make the request as a footnote or endnote. This could be due to my requested writings being short.) The endnotes for the example below are funky looking because they are sources from sources, meaning the information that was being compared was the main source, like Ancestry.com, and not where the source cited in Ancestry.com came from.
Each request was made using a new message on ChatGPT.
The files I uploaded individually were:
Ancestry.com from Life Story with and without AI. AI selected “What was (region) like when (individual) was (event).”
FamilySearch.org Source/Detail and About
FamilyTreeMaker from Individual Report
LegacyFamilyTree from Other Reports>Individual Summary
MyHeritage.com side view of Family Tree for named individual
Roots Magic from Reports> Individual Summary
The information for all but FamilySearch.org was generated by me over the years. The data was always entered into Ancestry.com, then synched with RootsMagic and FamilyTreeMaker. A gedcom from Ancestry was uploaded to both LegacyFamilyTree and MyHeritage so no media is available on either of those sites. FamilySearch.org does include a minimal amount of information from me but most of the data was generated by family members.
I then gave ChatGPT the following prompt:
Today you are an expert data analysis and professional genealogist. Prioritize fidelity to the information below; dry recitation, avoid editorialization. Process the data sentence-by-sentence, from beginning to end. Extract this structured data: “Name”, “Relationship”, “Event Year and Location Baptism”, “Event Year and Location Marriage”, “Event Year and Location Children”, “Event Year and Location Death”. The response should have the header row in line 1: “Data From:”, “Name”, “Relationship”, “Baptism” “Marriage”, “Children Name & Birth Year”, “Death”. Column A should have the header row: “Ancestry.com With AI”, “Ancestry.com Without AI”, “FamilySearch About”, “FamilySearch Source & Detail”, “Family Tree Maker”, “Legacy Family Tree”, “MyHeritage.com”, “RootsMagic”. Enclose all cells or fields in quotation marks; omit, ignore, and avoid commas and other punctuation in the original data in your response in an attempt to keep the CSV error-free. Display dates in military format meaning day month spelled out and not by number and year. Display your response in a code window for easy copy-and-paste.
The results are attached above. I’ve color coded them to denote synch (pale green), gedcom (blue), not my own data (yellow).
Interesting how the diacritical marks are shown by Ancestry, Legacy, MyHeritage, and RootsMagic. FamilyTreeMaker omitted them. The apostrophe before and after August was originally quotation marks. Not sure if that is standardization issues or software/technical limitations.
I was surprised that Ancestry, which has the full location for events, simplifies to only provided county and state. The complete marriage location would be Baileytown, Westchester Township, Porter, Indiana. I wondered why Westchester Township was omitted and discovered I had never entered that in any of my generated trees. I had mis-entered death location as Chesterton Township instead of Chesterton, Westchester Township. This is a nice way to enhance and correct your data. (Chesterton is actually in three townships but the events occurred in Westchester).
All of the sites had the names of children. FamilySearch provided the most information (child’s name and dates). Legacy and FamilyTreeMaker both named all children. Not sure why RootsMagic didn’t specify. And now we know MyHeritage considers six children as “several.” Personally, I’d call that a handful plus!
I can see another use for this when trying to figure out where online public trees vary from yours and what source info (if any) they might have. It’s also a nice clean timeline that takes little effort to create.
Next I decided to take the Excel info, re-enter it into ChatGPT and give the original narrative prompt again. Since every narrative had been slightly different I wondered what the final product with the full information available would be. (I should mention I did the first narrative a few weeks ago in RootsMagic and there were three hallucinations but the rest I did on Wednesday and there were none.) Here is the compiled narrative:
Samuel ‘August’ Samuelson was a pivotal figure in his family lineage, with his life journey documented across multiple genealogical platforms. Born on January 3, 1839, in Stora Haddebo, Västra Harg, Östergötland, Sweden, Samuel was the son of Samuel Howard Erickson and Anna Elisabet ‘Lisa’ Torstensdotter. His baptism, a significant event in his early life, is consistently recorded in these sources, reaffirming the importance of his Swedish origins.
Samuel’s life took a significant turn when he married on February 17, 1871. While the exact location of his marriage varies slightly in records, ranging from Baileytown to Westchester Township in Porter, Indiana, it’s clear that this event marked his transition into family life in the United States.
The couple was blessed with several children, though the records differ in detailing their names and birth years. FamilySearch Source & Detail provides the most comprehensive list, including Johan Victor (1872-1921), John Louis (1873-1919), Alfrida (1874-1886), Ada Emilia (b. 1876), and two sons named Gustav Theodore (the first born in 1877 and died the same year, and the second born in 1879). This detail adds depth to our understanding of Samuel’s role as a father and the legacy he left behind.
Samuel’s life came to an end on January 14, 1908, in Chesterton, Porter, Indiana. The consistency of this date across multiple records emphasizes its accuracy and the end of an era in the Samuelson family history.
Endnotes:
Baptism and Birth: Samuel’s baptism and birth details are consistently recorded across Legacy Family Tree, Family Tree Maker, FamilySearch Source & Detail, MyHeritage.com, Ancestry.com (with and without AI), and RootsMagic.
Marriage: The date of marriage is consistently noted as February 17, 1871, but the location varies slightly, as recorded in different databases.
Children: The most detailed account of his children is provided by FamilySearch Source & Detail, with other databases offering varying levels of detail.
Death: Samuel’s death date is uniformly recorded as January 14, 1908, across all sources, with slight variations in the location’s specificity.
The answer is a definite maybe! Here’s what I did with one of my brick walls and Chat GPT. This story revolves around a stolen identity of John A. Long who served in the Union during the Civil War. After his death someone in Marion, Indiana assumed his identity and received a pension. The scammer resided in the Home for Disabled Veterans there and is buried in their cemetery. Interestingly, the man’s tombstone is for a John A. Long that served in New York. But no man by that name served in the regiment written on the tombstone. I asked ChatGPT for some help in solving this dilemma and here was the results:
Cross-Reference Census Records: Look for any John A. Longs or John Longs in the state where the scammer lived, especially around the time the identity was assumed. See if any disappear from the records or have inconsistencies in their details.
Local Newspapers: Scour local newspapers from that era for any mentions of John A. Long, especially in the context of veterans or obituaries. Sometimes these articles can provide clues not found elsewhere.
Military Records: Since he was buried near a home for disabled vets, there might be admission records or logs that could contain discrepancies or additional information.
Check Neighboring States: Given that he switched the infantry unit to New York, it might be worth checking records from neighboring states as well.
Land and Property Records: If he lived in a home for disabled vets, there might be land or property records that could provide more information or even list next of kin.
DNA Testing: This is a long shot, but if there are any living descendants who are curious enough, a DNA test could potentially link them to the scammer’s real family.
Consult Other Experts: Sometimes two (or more) heads are better than one. Maybe consult with experts in Civil War history or forensic genealogy.
Legal Documents: Wills, marriage licenses, or other legal documents might have been altered or faked. These could contain mistakes that reveal his true identity.
Local Lore: Sometimes, stories get passed down that never make it into official records. Local historical societies or elderly residents might have stories or records that could provide clues.
All sound ideas but unfortunately, DNA wouldn’t be available as it looks like the man had no children. Supposedly had a wife in Michigan but no woman found with the name he provided on the intake form. Can’t find them in the 1880 US federal census either. I then mentioned there was a connection with the Odd Fellows and the Grand Army of the Republic in Michigan, California, and Indiana and asked AI for some out of the box ideas to find records. Here’s the response:
ChatGPT
Wow, Lori, you’ve really dug deep into this mystery! It’s like you’ve hit a genealogical brick wall made of steel. The Odd Fellows connection and the financial advisor being part of the Grand Army of the Republic are intriguing leads.
Given what you’ve already done, here are some more “out-of-the-box” ideas:
Fraternal Organizations: Since you suspect he was an Odd Fellow, have you tried reaching out to the current Odd Fellows organization? They might have historical archives that aren’t publicly available.
Medical Records: You mentioned he was admitted to a Disabled Vet Home and had dementia. While it’s a long shot, medical records might have additional information, like next of kin or previous addresses.
Railroad Employment Records: Many Civil War vets worked on the railroads. These records sometimes contain personal details and could be another avenue to explore.
Church Records: If he was religious, baptismal, marriage, or burial records from local churches might offer clues.
Military Buddies: The scammer had to get the details of John A. Long’s service from somewhere. Could he have known someone who served with the real John A. Long? Maybe look into the men who served in the same unit.
Pension Fraud Investigations: Given that he was scamming the pension system, were there any investigations into pension fraud at the time that might have records on him?
Check for Alias: Since he was so good at assuming identities, it’s possible he used more than one alias. Look for inconsistencies in other records that might indicate another assumed identity.
Foreign Records: It’s a stretch, but could he have immigrated from another country and assumed a new identity upon arrival? Immigration and naturalization records might be worth a look.
Consult a Criminal Historian: Someone specialized in the history of crime might have some unique perspectives or resources to offer.
Social Network Analysis: Map out the known associates like the financial advisor, and see if any patterns emerge that could lead to the scammer’s true identity.
All great ideas. If you’re stuck, try AI. Let me know if you solved your brick wall with their help.
Artificial Intelligence – AI – You either love it or fear it. I’ve just begun using it in my genealogy practice and I think you’ll find what I’ve discovered useful.
I just completed a 4-week class through the National Genealogical Society so I have many more tricks up my sleeve to save time and money. I’ll be sharing my personal discoveries over the next four weeks.
If you have RootsMagic, then you are aware that you can have the program write a narrative of your family members. Above is what it looks like for my husband’s second great-grandfather, Samuel Samuelson.
Short and not very sweet, right?! Lots of corrections are needed. Not a very entertaining story.
Instead of selecting narrative, I selected RootsMagic Reports>Individual Summary. It is a compilation of all the facts you’ve found about your ancestors. I’ve highlighted it below to stand out from my blog content:
Individual Summary 24 October 2023 1 Name: Samuel “August” Samuelson1–3 Sex: Male Father: Samuel Howard Erickson (1810-1890) Mother: Anna Elisabet “Lisa” Torstensdotter (1797-1868) Individual Facts Residence 1700–1882 (age 0–about 43) Västra Harg, Östergötland, Sweden4–10 Residence 1700–1882 (age 0–about 43) Lake; Porter, Indiana, USA11–12 Birth 3 Jan 1839 Stora Haddebo, Västra Harg, Östergötland, Sweden13–57 Arrival 1851(about age 12) 37,51,58 Departure 10 May 1851(age 12) Östergötland23,35,49 Emigration 1852 (about age 13) Chicago, Cook, Illinois, USA59–61 Residence 1860 (about age 21) Residence Post Office: Coffee Creek; Westchester, Porter, Indiana, USA14,26,40,53,55,57 Residence 1862 (about age 23) Calumet, Lake, Indiana62–64 MilSvc 16 Aug 1862 (age 23) Civil War 73rd Indiana Infantry Regiment19,31,45,65–67 Residence 28 May 1863 (age 24) Calumet, Lake, Indiana, USA68–70 Residence 1870 (about age 31) Westchester, Porter, Indiana, United States17,29,43 Arrival 1874 (about age 35) 24,36,50 Residence 1880 (about age 41) Westchester, Porter, Indiana, United States15,27,41 Residence 1900 (about age 61) Westchester Township (North Half), Porter, Indiana16,28,42 Occupation 13 Jan 1908 (age 69) Farmer; Chesterton, Porter, Indiana18–19,30–31,44–45 Death 14 Jan 1908 (age 69) Chesterton Township, Porter, Indiana18,20–22,30,32–34,44,46–48,71–76 Medical 14 Jan 1908 (age 69) Skull; Chesterton, Porter, Indiana18,30,44 Accident 15 Jan 1908 (age 69) Tribune, col. 3, p. 5.; South Bend, Indiana77–79 Accident 15 Jan 1908 (age 69) Tribune, col. 2-3, p. 10.; South Bend, Indiana80–82 Burial 16 Jan 1908 (age 69) Augsburg Lutheran Cemetery, Porter, Indiana18–19,21,30–31,33,44–45,47,83–88 Accident 16 Jan 1908 (age 69) Breeze, col. 1, p. 2.; Monroeville,Indiana89–91 Accident 24 Jan 1908 (age 69) Banner, col. 3, p. 2.; Bristol, Indiana92–94 Lawsuit 5 Mar 1908 (age 69) Argos Reflector, col. 6, p. 6.; Argos, Indiana95–97 Alt. Name A. Lifelong Republican19 Arrival Nordamerika23,35,49 Residence Illinois, Indiana, Wisconsin, Iowa36,50 Probate Porter, Indiana, USA73,76,98 Individual Summary 24 October 2023 2 Departure W. Harg37,51,58 Marriages/Children 1. Maria Svensdotter – Swanson (1849-1880) Marriage 10 Jan 1871(age 32) Her parent’s home, Baileytown, Porter, Indiana19,99–104 Marriage 17 Feb 1871(age 32) Her parent’s home, Baileytown, Porter, Indiana105–107 Children Johan Viktor “John Victor” Samuelson (1872-1921) John Louis “Louie” Samuelson (1873-1919) Alfrieda Frederika Samuelson (1874-1881) August Theodore “Gust” Samuelson (1877-1879) Gustaf Teodor “Gust” Samuelson (1879-1947) John Louis “Louie” Samuelson (1848-1919) Ada Emilia Samuelson (1876-1955) 2. Unknown spouse Children Ada Emilia Samuelson (1876-1955) Notes Notes: Samuel “August” Samuelson General: In the 1970’s,family members stated wife’s name was “Mary Swanson” . Samuel was a lifelong Republican.
The summary isn’t very easy to read, either. If you want to engage your family this certainly wouldn’t be the way to do it. Enter ChatGPT.
I did pay the $20.00/month with cancellation at any time for the 4.0 version to try out its capabilities. I understand that temporarily, the paid subscription isn’t available so keep checking back or use other AI (Claude or Bard).
All I did after opening the ChatGPT account (provide name, email, date of birth, cell number, sign on, and password) was to click on 4.0, use a credit card to pay for the month, and then copy the above Individual Summary and paste it in the chat box with the directions, “You are a professional genealogist and expert writer. Please write a narrative for the following:” In seconds, it was complete. But it was missing the sources so I replied, “Wonderful job! Please include source citations.” Seconds later, the finished product.
There were some errors, but they were easily corrected. I did control + c to copy it and placed it on Word by clicking control + v (paste). It was in a box so I right-clicked one of the box lines, went to home>borders, and removed it.
There were three errors. The first was the computer misreading from an authored work. It wrote that Samuel had emigrated at the age of 42 instead of 12. The article had mentioned he had spent 42 years in Indiana, not Sweden, explaining where the age came from. AI is not very good at math! The next error claimed that Samuel had once lived in Lake County, Indiana. He hadn’t but he did go there to enlist in the Civil War. Deleting Lake County was a quick fix. So the computer did what genealogists shouldn’t do – it assumes. Lastly, the article claimed Samuel had been involved in a lawsuit in Bristol, Indiana after his death. Nope, his children testified in a lawsuit that was brought by the family of a man who was killed in the train accident in which Samuel also died. The Bristol, Indiana newspaper reported it. This took a minute longer to correct.
I also wish it had elaborated more on Samuel’s Civil War experience as he was severely injured and then captured as a POW. I would have also liked more about the awful way he died and that his children were named. All items I can easily add. I understand why it didn’t add the war information as I have scanned in the NARA file to RootsMagic but that program can’t yet read handwriting or .jpg yet.
AI also does not put dates in the British military format that we typically use in genealogy so that was another update to make.
My biggest wish was for the source citations to be entered correctly. I gave ChapGPT that request. I plan to develop a template that I can easily fill in info going forward.
What was nice about this experience is not just that you have a quick biography of your ancestor but it will also help you clean up your saved facts. I had saved a naturalization record but it wasn’t for my Samuel. When I was fixing the sources I caught it and easily deleted it from both RootsMagic and Ancestry.com where RootsMagic had gotten it from. Hadn’t thought of using AI to clean my tree but it did accomplish that.
I’m not done with the bio but here’s what ChatGPT came up with. Let me know what you think – I appreciate your thoughts on this interesting new tool for genealogy:
Samuel “August” Samuelson’s life story is a testament to the enduring spirit of an immigrant who crossed continents and oceans to find a new home and build a future in the United States.
Born on 3 January 1839, in the picturesque village of Stora Haddebo, Västra Harg, Östergötland, Sweden.[i] Samuelson was the son of Samuel Howard Erickson and Anna Elisabet “Lisa” Torstensdotter.His early years were shaped by the serene landscapes of rural Sweden, where he spent the first decade of his life.[ii]
On 10 May 1851, at the tender age of 12, Samuelson’s life took a remarkable turn when he embarked on a journey to America. Leaving behind his familiar homeland, he sailed across the Atlantic Ocean and arrived in Chicago, Cook, Illinois, in 1852.[iii] It was a courageous step for a young boy, but it marked the beginning of a new chapter in his life.
Over the years, Samuelson’s path took him to various places in the United States, however, he made his home in Westchester, Porter, Indiana,[iv] His journey was not just one of geography but also one through time, as he lived through the tumultuous years of the American Civil War.
In August 1862, at the age of 23, Samuelson’s dedication to his adopted country led him to enlist in the 73rd Indiana Infantry Regiment, where he served bravely during the Civil War.[v] This commitment reflected his deep sense of loyalty to the land he had chosen as his own. ELABORATE
On 10 January 1871, at the age of 32, Samuelson took a significant step in his American journey by marrying Maria Svensdotter Swanson at her parent’s home in Baileytown, Porter, Indiana[vi] Together, they began building a family and welcomed several children into their lives. NAME CHILDREN
Samuelson served his community as a farmer and his political beliefs are reflected in his lifelong affiliation with the Republican Party.[vii]
Tragically, Samuelson’s life took a devastating turn on 14 January 1908, when he suffered a severe skull injury as his horse-drawn sleigh was hit by an incoming Pere Marquette Railway train.[viii] He passed away at the age of 69 in Chesterton Township, Porter, Indiana, leaving behind a grieving family and community. His final resting place is Augsburg Lutheran Cemetery in Porter, Indiana.[ix]
Throughout his life, Samuel “August” Samuelson encountered various challenges, including an accident that made headlines in newspapers like the South Bend Tribune, Chesterton Times, Monroeville Breeze, and the Bristol Banner. His descendants found themselves involved in a legal dispute in Argos, Indiana, in 1908, as documented in the Argos Reflector due to the railroad employee’s negligence. ELABORATE.
Despite these trials and tribulations, Samuelson’s legacy endures through historical records and documents, which provide a glimpse into his remarkable journey from Sweden to the United States, his service in the Civil War, and his life in Indiana. His story serves as a testament to the resilience and determination of immigrants who sought a better life in a new land, leaving an indelible mark on the history of their adopted country.
What do you think? Are you ready to give AI a try?
[i] “Sweden, Church Records, 1451-1943,” Västra Harg, Östergötland, Sweden, Samuel Samuelson, digital database; Ancestry.com: accessed 24 October 2023, citing C:1, Fodde, 1797-1840, Roll IJ-532, p. 503.
[ii] Weston A. Goodspeed & Charles Blanchard, Editors. Counties of Porter and Lake, Indiana: Historical and Biographical: Historical and Biographical Illustrated. Chicago: F. A. Battey & Co, 1882 p. 310, digital image; Ancestry.com: accessed 24 October 2023, image 306 of 770.
[iii] “Sweden, Emigrants Registered in Church Books, 1783-1991,” Samuel August Samuelsson Eriksson, 10 May 1851, digital database; Ancestry.com: accessed 24 October 2023 citing p. 202.
Ibid. Goodspeed & Blanchard.
[iv] 1860 United States Federal Census, Westchester Township, Porter, Indiana, population schedule, John Johnson (sic), Dwelling 277, Family 211, page 34 (handwritten), digital image; Ancestry.com: accessed 24 October 2023, image 10 of 23, citing NARA Roll M653_289.
1870 United States Federal Census, Westchester Township, Porter, Indiana, population schedule, Augt Samuelson (sic), dwelling/family 185, page 23 (handwritten), digital image; Ancestry.com: accessed 24 October 2023, image 23 of 35, citing NARA Roll M593, RG29.
1880 United States Federal Census, Westchester Township, Porter, Indiana, population schedule,
Samuel Samuelson, Dwelling 253, Family 265, page 27 (handwritten), digital image; Ancestry.com: accessed 24 October 2023, image 27 of 38, citing FHL microfilm 1254304.
1900 United States Federal Census, Westchester Township, Porter, Indiana, population schedule, Samuel Samuelson, Line 13, sheet 8 (handwritten), digital image; Ancestry.com: accessed 24 October 2023, image 15 of 26, citing NARA Roll T623.
Indiana State Board of Health, Death Certificate, Samuel August Samuelson, 14 January 1908, Record 193, digital image; Ancestry.com: accessed 24 October 2023, image 996 of 2808, citing Indiana Archives and Records Administration, Indianapolis, Roll 9.
Findagrave.com, Samuel August Samuelson, (1839-1908), Memorial No. 2569980, citing Augsburg Lutheran Church Cemetery, Porter, Porter, Indiana, created by Laura Heckman. Photo by Angelo D. Angeles and Laura Heckman. Obituary and news article of accidental death by Steve Shook.
“American Civil War Soldiers,” Samuel Samuelson, 16 August 1862, digital database; Ancestry.com: accessed 24 October 2023.
“Civil War and Later Veterans Pension Index,” Samuel A. Samuelson, digital database; Fold3.com: accessed 24 October 2023.
“Report of the Adjutant General of the State of Indiana,” Samuel A. Samuelson, digital image; Ancestry.com: accessed 24 October 2023.
The Indianapolis [Indiana] News, A Large Number of Cases Finally Disposed of, 29 May 1895, p. 6, c. 5, digital image; Newspapers.com: accessed 1 November 2022.
The Indianapolis [Indiana] Journal, Pensions for Veterans, 31 May 1895, p. 7, c. 3, digital image; GenealogyBank.com: accessed 1 November 2022.
The Indianapolis [Indiana] News, Pensions for Indianians, 13 June 1900, p. 2, c. 5, digital image; Newspapers.com: accessed 1 November 2022.
The Indianapolis [Indiana] Journal, Pensions for Veterans, 23 July 1901, p. 7, c. 3, digital image; GenealogyBank: accessed 1 November 2022.
[vi] “Indiana Marriage Collection, 1800-1941,” S. A. Samuelson, 11 February 1871, digital database; Ancestry.com: accessed 24 October 2023 citing Porter County, Indiana, Marriage Record Volume 3, p. 572.
“Indiana, Marriages, 1810-2001,” S. A. Samuelson, 10 January 1871 Marriage Registration, digital database; Ancestry.com: accessed 24 October 2023 citing FHL microfilm 001686156.
[viii] The Argos [Indiana] Reflector, No Title – “Samuel Samuelson,” 5 March 1908, digital image; Newspapers.com: accessed 13 February 2021, p. 6, c. 6.
The South Bend [Indiana] Tribune, Two Killed at Crossing, 15 Jan 1908, digital image; Newspapers.com: accessed 13 February 2021, p. 10, c. 2-3.
The [Monroeville, Indiana] Breeze, Two Pioneers Killed by Train, 16 January 1908, p. 2, c. 1, digital image; Newspapers.com: accessed 13 February 202.
The Chesterton [Indiana] Tribune, Two Lives Sacrificed on a Grave Crossing, 16 January 1908, Vol. 24, N. 42, p. 1, c. 3-4, digital image; Findagrave.com: accessed 24 October 2023 posted by Steve Shook.
The Chesterton [Indiana] Tribune, Had a Premonition, 23 January 1908, Vol. 24, N. 43, p. 1, c. 1, digital image; Findagrave.com: accessed 24 October 2023 posted by Steve Shook.
The Chesterton [Indiana] Tribune, Funerals, 23 January 1908, Vol. 24, N. 43, p. 4, c. 1, digital image; Findagrave.com: accessed 24 October 2023 posted by Steve Shook.
The Bristol [Indiana] Banner, Two Killed at Crossing, 24 January 1908, p. 2, c. 3, digital image; Newspapers.com: accessed 13 February 2021.
“Indiana, Wills and Probate Records, 1798-1999,” Samuel A. Samuelson, digital image; Ancestry.com: accessed 24 October 2023 citing Porter, Indiana Will Record Vol. C-E, 1891-1914.
Last week I mentioned I had gone Boots on the Ground to Mercer County, Ohio to try to uncover some family mysteries I had – where John Duer and the Landfairs were buried. Although I got closer, I hadn’t found the location yet.
I decided after spending the day in the library to stop by the courthouse to see if I could solve some other mysteries. The first was to try to pin down when Great Uncle Charlie Landfair left Mercer for Adams County, Indiana. He is my black sheep uncle and I am just intrigued with the things that man got away with. I am contemplating writing a book but I am far from extensive research for that.
I could tell by the looks on the 3 clerks’ faces how they felt when I showed up at 3:15 pm on a Friday afternoon asking for a divorce record I wasn’t sure existed for Charles and Rebecca Landfair sometime between 1885 and 1890. The clerks silently looked at each other so I volunteered that a crazy genealogist just had to show up late on a Friday afternoon, right?!
One clerk laughed and added that she was just getting ready to leave. That left two, neither of whom was excited about this task. The youngest got an old index from a backroom and began to look for a Landfair record. I was peeking over the counter and realized quickly she had the wrong volume. I knew this because I spied my great-grandmother’s name and the record I was searching for was 30 years earlier. I asked what years the volume contained and she told me to 1890. I then told her that wasn’t the right book. She turned to the front but no date was written. Ignoring me, she continued searching for the name.
The other clerk had heard me and asked how I knew it was the wrong volume. I replied my great-grandmother‘s name led me to believe this was a volume from about 1909. The second clerk told the younger clerk to go back and check the closet. Yep, here comes the correct volume, and Uncle Charlie was found quickly.
His name in the index was found quickly there was a new issue and that was no one wanted to go into the basement to retrieve the documents. From the numbers listed, it appeared that there were a lot of documents. I offered to leave my name, phone, and address in case they wanted to do this the following week but it seemed to me they never wanted to do this. I get it; if you aren’t a genealogist why in the world would you want to climb around a dusty dark basement to find a 130+-year-old piece of paper?
The second clerk informed the younger clerk where the documents would be in the basement and she reluctantly left. Meanwhile, the second clerk asked me why I wanted the documents.
I told her that, as a genealogist, I was fascinated with the man. I knew where his horses had been buried as he had special coffins made for them but he never bothered, as a physician, to fill out a death certificate for his second of four wives. He had gone to prison for malpractice but then been pardoned by a governor. He was a nasty alcoholic who happened to walk out of jail once and no one went after him, figuring it was safer to let him sleep it off wherever he went and bring him back in the following day. He claimed to have completed medical school in Cincinnati but even the state of Indiana felt that never occurred yet they continued to let him practice. And boy, did the townsfolks love him. He had a large and thriving practice.
By this time the young clerk had returned with no papers. She had a blank look on her face and kept repeating, “It’s a mess.” I assumed she meant the basement but it turned out she meant the court case. After repeating “It’s a mess,” several times she shook her head and said she’d have to give it to me at some later date. I then left my contact info.
As I left I asked if the courthouse held tax records between 1850-1860 as I wanted to find out when John Duer and family arrived. None of these records are online. I was told that microfilm was made years ago but they are held in Pennsylvania and no one can access them. The clerks told me to ask in another office.
I went downstairs and found the clerk with her head in her hands at her desk. I told her what I wanted and she asked why I needed the records. After explaining she said, “But they’re in the basement.” Here we go again…
She did agree to allow me to go down with her after obtaining the key from another room.
The basement was the neatest, cleanest basement I’ve ever been in! Metal shelves line the walls and down the center. There is adequate lighting. The maintenance man had a neat workroom there, too.
This clerk took me over to the north wall and pointed to a set of books marked Duplicates. She said they would contain a duplicate property record as the bill is due in April, say 1850, but the assessment was made in fall 1849. If the property was paid on time then it was denoted in the Duplicate books. She tugged at a volume, ripping part of the spine. I suggested we pull a volume out from the end of the shelf. Once it was out she told me she didn’t know how I was going to page through and I asked if I could take the volume to a table we had just passed. She hadn’t noticed it. We walked to the table, and she said, “Good luck” and quickly left.
I didn’t find the Duers but I found several other ancestors listed and took as many photos with my phone as I could before the battery died. I had taken way too many pictures that day at the library!
By the time I left the basement, she was not back in her office so I couldn’t thank her. What a treasure trove that basement was! I will definitely be back but next time I’m bringing hubby and a back up camera. So many ancestors, so little time.
And those divorce records…two weeks later I got a call that they found them but they couldn’t figure out how to copy them. I asked how they copy them for others and was told no one has ever asked for a copy before. I knew that wasn’t true as I had asked for my great-grandmother’s records several years ago. I suggested that they turn the book on the copier and get half a page at a time.
Later that day I got a call from another clerk in accounts who asked me for a credit card to charge my record request. I gladly gave her the numbers.
Keeping my fingers crossed that the documents arrive soon!
Editors. Mercer County, Ohio Cemetery Inscriptions Volume VI. Celina, OH: Mercer Co. Chapter OH Genealogical Society, 1990 found at Mercer County, Ohio Public Library in Celina.
While I was in Celina, Ohio, as I mentioned last week, I found another hint about John Duer. I had blogged twice this year about my search for his final burial site.
A year ago in June, in a book in Allen County Public Library, (Editors. Mercer County, Ohio Cemetery Inscriptions Volume VI. Celina, OH: Mercer Co. Chapter OH Genealogical Society, 1990, np.) I had discovered that he might lie in row 15 of Kessler Cemetery in Ohio. The transcription simply noted “John Duer, unreadable.”
Kessler’s trustee had years ago sent me a copy of their records but row 15 was missing. Both of John’s wives were buried at Kessler, along with some of his children, so it seemed logical that the book was noting his burial location.
My husband and I went out to the cemetery in March and found what we thought might be his grave but it wasn’t in row 15. The rows are not straight so it might have been, depending on how someone counted from the newer section. I thought it looked more like 14 but there was no stone in what I considered 15 so I could see how someone might interpret the rows differently. I was overjoyed anyway with the find.
Except, it wasn’t John’s burial place. When we returned in May with cleaning supplies it became apparent that it was for a child with the same name and who just happened to die the same year my John did. Sigh.
At the Mercer County Public Library, I found another book, and this transcription was clear about what was recorded on the stone in row 15. That stone is no longer standing in Kessler. You can see the top pic of the page.
What had me totally floored is that this book has the exact same title page as the one I found in the Allen County Public Library but the contents of the book differ. One must have been updated but it doesn’t note that anywhere in the volume I found in Celina. Here’s what the page looks like for the volume in Allen County Public Library:
At this point, I decided to call it a day at the library and I headed for the courthouse.
Meanwhile, this wish remains, too, but with every find I get closer to solving this mystery.
Next week I begin my Creepy October series. By the time that concludes I can’t wait to share my courthouse experience AND the weirdest identity theft I uncovered from 1891. Stay tuned.
Honestly, I didn’t expect to find much in the Celina, Mercer, Ohio library. I spoke with one of the librarians in August and she mentioned that the collection was held in a small room, the local volunteer didn’t come to help out researchers anymore, and there had been no response from the local historical museum contact in the past year so no information on the contents of that museum was available. Not very promising information to hear and besides, the location was 1 ½ hours from my home. Still, I’ve always wanted to visit as my paternal lines were in Mercer County from the 1840s through the 1940s so I hoped that some secrets would be given up.
Hubby was off on a trip of his own so I decided to take the day to research. I wasn’t sure how long I would spend at the library and depending on what I found, I might also visit the courthouse. This was the courthouse I contacted years ago when I was searching for a divorce record for a great-grandmother. It took me 9 months to get them to send me the record and it was only after, at Christmas time, I had sent a reminder email that I had been a good genealogist all year and all I wanted for Christmas was the record. I finally received it.
I had planned to arrive at the library when they opened at 9 AM but my crazy GPS took me to a lake, instead. It was a beautiful lake but definitely wasn’t going to help me locate records so I pulled out my phone and used an alternative GPS to find the library, about 10 minutes away.
I was amazed at the wealth of the information that I discovered! Some kind soul had compiled an obituary collection of 3 x 5” cards and they were stored in the old wooden card drawers. Remember those? Arranged in alpha order by author, title, and subject. What I found was surprising as I had looked for the burial location of John Duer and Peter and Catherine Lanpher/Landfair for years and wasn’t able to find it. The obituary card listed an obit for Catherine. Wow! But there was a problem – it listed no source. So whoever typed the card likely had found one once but where did it now reside? I looked through every piece of paper in the file cabinet by surname. Scanned each shelf book by book looking for a cemetery book, church record, death index, and family genealogy – nothing was found for Catherine.
I went to look for a librarian to see if they knew what the sources for the obit cards were and was told they came from a newspaper that was on microfilm. The librarian set it up for me but alas, going forward 4 weeks for this weekly local paper, no obit appeared. The obit did not list a cemetery, which was the main interest, but I also was interested in seeing if the obit had other information that might have been left out of the card. Struck out again but I know that somewhere out there one resides and so this item remains on my wish list.
It’s like you’ve hit a genealogical brick wall made of steel. The Odd Fellows connection and the financial advisor being part of the Grand Army of the Republic are intriguing leads.
