I think I have a genuine need for an #LLM. Can someone tell me if this is possible?

@openbenches contains ~40k text inscriptions.

Someone wants to know how many are dedicated to men, how many to women.

"To Grandma Sylvia" is obvious.
"To R Smith" is not.

Could an AI give a rough estimate of the gender of a subject?

Could it ignore text relating to who the inscription is from? "To Granny from Dave and Alice".

What would be the most accurate / cheapest / fastest / easiest tool to work with?

@Edent @openbenches We wrote some code for that: https://github.com/mysociety/gender-detect , could add some regex on top to spot if it’s from/to?
We’ve used llm to create regex: https://www.mysociety.org/2025/08/12/using-llms-to-write-categorisation-rules/
But I wouldn’t trust it to do the actual thing.
GitHub - mysociety/gender-detect: Python package to guess gender from name

Python package to guess gender from name. Contribute to mysociety/gender-detect development by creating an account on GitHub.

GitHub
@dracos that is detailed and useful! Cheers.