The result to aim for
Lucie Moraine-Brochet, a professor at the Toulouse Academy, asked ChatGPT for an exercise to identify the expansions of the name for her students. No sentence had any relative subordinate: she kept the exercise so that the class would mark the forgotten.
What was done
Educational Café (10 February 2025). Nicolas Bannier (personalised correction considered unstable): same article, out of wave — a test to conclude that the tool is not suitable is not a case of use. Here the chosen gesture is the exercise used in class. No copy is published.
Before you start
Tool cited by the source: ChatGPT. Fill in the bracketed items: [5e / 4e]. Strip confidential data that is not needed and check your tool’s access terms. Features and plans can change.
The method, in three steps.
Gather the context
Spot the bracketed items in the prompt (
[5e / 4e]) and prepare what they ask for.Adapt the prompt
Copy the prompt below, replace the bracketed items, then paste it into ChatGPT.
Reread before using
Reread the result, correct it if needed and keep the final decision. Caveats are detailed below.
Your starting point.
Replace the bracketed items, then adapt the proposal to your situation. This prompt is written by the iadujour desk It is not a quotation from the source.
Level (facts): [5e / 4e]. Notion: expansion of the name (epithet, addition of name, relative). Suggest 8 sentences. Each type must appear at least twice, including one relative. If you can't, say it. Do not write the correction to paste to the table.
What deserves your attention
Proof level: Testimony published by an identified source. Source checked on 10 November 2026. Use described by the source, not tested by the desk. Original summary written by iadujour.fr: figures and claims are the source’s; the prompt is a desk proposal, not a quotation.
Comments.
A field note, a question, a precision on this use case? Comments are reviewed before publication.
Published comments
Loading comments…
Leave a comment
Moderation charter. Every comment is reviewed before publication. We refuse hate speech, insulting or discriminatory language, advertising, spam and promotional links, off-topic posts and other people’s personal data.