Separate land descriptions in an 1836 dower record with ChatGPT
- Posted
- by Heartland Genealogy
- Last checked
- Method:
- How we verify
Evidence: Described by posterThe person describes what happened in words, without screenshots or video.
Outcome
Working from an 1836 Jefferson County, Indiana, probate record, the Heartland Genealogy blogger asked ChatGPT to pull out the land description. It separated Thomas D. Crawford's 113-acre tract from the 43¾ acres set aside as the dower of Crawford's widow, Jane. While drafting a blog post from the record, ChatGPT also found that this Jane appeared to be Jane Todd Crawford, remembered in medical history for surviving an operation performed by Dr. Ephraim McDowell. The writer treats it as a lead to keep researching: 'AI found the connection. It didn't finish the research.'
AI tool
Prompt Recreated prompt
The source didn't share its exact prompt, so we wrote this from what it describes.
Here's my transcription of an 1836 probate record (a widow's petition for dower). Pull out the land description, and separate the description of the whole tract from the part assigned to the widow.
Try this in:
Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini opens empty, so we copy the prompt for you to paste. Every button also copies it.
Opens in a new tab. We don't see what you send.
These links are only a shortcut. We're not affiliated with OpenAI, Google or xAI, and your results may not match the source.
Optional stronger version
Our rewrite with extra checks. The poster didn't test it.
Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish. Goal: Help me understand an old record: pull out the key facts and land descriptions, and suggest leads I can check. Questions to ask me first: - What kind of record is it, and where and when is it from? - Do I have a transcription, an image, or both? - Which people in it am I researching? Inputs (fill in or confirm): - Transcription or image of the record: [RECORD] - Place and date: [PLACE AND DATE] - People of interest and any IDs from my family tree site: [PEOPLE] Rules: - Quote the record's own words for every fact you pull out. - Keep separate descriptions separate (for example a whole tract and a portion assigned to someone), with acreage and boundaries as written. - Explain old legal or surveying terms in plain English. - Label any outside information as a lead with its source, never as a confirmed fact. - Never invent names, dates, relationships or citations. Checkpoint: Show me the extracted facts and land descriptions before you look for outside information. If you get stuck: If the handwriting or transcription is unclear, flag the exact words and give possible readings rather than choosing one silently. Verify before you finish: Check every extracted figure (acres, dates, names) against the record text, and list which leads still need a primary source. Output: A fact summary with quotes, the separated land descriptions, and a list of leads with what record would confirm each. Done when: I have the record's facts straight and a short, sourced to-do list for the next research step.
Source
https://www.heartlandgenealogy.org/2026/08/when-ai-connected-dower-record-to-piece.html
Related cases
- Trace a family tree from half-remembered details with ChatGPT (partial)Recreated promptEvidence: Described by posterPartial
Ryan Aubrey didn't know where the family came from, or even the grandparents' middle names. Aubrey turned ChatGPT's effort level up as high as it would go and shared everything known, mistakes included. On the father's side it quickly found a grandfather's obituary (a high school state championship and a basketball scholarship to the University of Tampa) and went through FamilySearch and Find a Grave to suggest a colonial Virginia line of 'Awbrey's' with a possible, unconfirmed Welsh origin. On the mother's side the line got lost after the grandparents in West Virginia, so Aubrey says the next step is to 'go analog'.
ChatGPT · Research · Source date:
- Report global NAND market share with Gemini Deep ResearchImproved promptEvidence: Screenshots or logsFailure
Asked for a simple report on global NAND market share, Gemini Deep Research returned figures the poster called an incredible failure when compared with Sandisk's investor-day slide and Claude's answer to the same query.
Gemini Deep Research · Research · Source date:
- Write a one-page sales brief on a target company with ManusRecreated promptEvidence: Article or interview
Asked for a B2B sales brief on Google for a tl;dv pitch, Manus produced a one-page brief with revenue, tech stack, key decision makers, recent announcements and a sourced section mapping Google's pain points to tl;dv features; the reviewer says it took two minutes.
Poster says:About two minutes
Manus · Research · Source date: