Skip to content
UsecaseBoard
← All use cases
blogFamily History

Match first names in an old letter to a small family-tree export

At a glance

A genealogist uses ChatGPT to find related name groups in a GEDCOM file and checks the proposed identities. This workflow is listed under Family History, Research, Personal Archives.

Agents / tools
ChatGPT, Ancestry, GEDCOM, Text editor

SourceBuilding a tool for these workflows? See weekly rates.

What they did

1) Setup: Have access to the family tree and review whether its personal information may be shared. In Ancestry's tree view, open the three-dot menu → Tree Settings → Export tree → Download your GEDCOM file. Use a small tree for the demonstrated approach. 2) Start a fresh ChatGPT conversation. Describe the genealogist role and the names from the letter, then request matching family groups with full names and relationships to a named anchor person. 3) Open the downloaded GEDCOM in a text editor, copy its text, and submit it to the conversation. 4) Finish: Ask for a double-check and explanation, compare the proposed relationships with the tree, and treat the matches as research clues for further investigation.

How it went

The author's fictional test found the correct group; larger trees and repeated follow-up searches produced problems.

Worth knowing

This is a 2023 proof of concept. The article's size limit is historical, and GEDCOM exports can contain private facts.

Save ideas in this browser. Upvotes count across the board.

Prompt excerpt

No prompt excerpt was provided by the source.

Sponsored

CodeBuddy

Tencent Cloud AI coding assistant for IDE and CLI.

Try CodeBuddy ↗
Explore all →