[PaulHoule]

There is a lot of work on neurosymbolic systems, see this review

https://arxiv.org/pdf/2305.00813.pdf

I'd note that it would be much more powerful to produce code to run in an SMT solver

https://en.wikipedia.org/wiki/Satisfiability_modulo_theories

as opposed to Prolog. It's clear to me how you can get the LLM to generate code for such a system but many of the tough problems about decidibility are as tough as they ever were. On top of that there is the problem of efficient logical inference. For instance the Cyc system

https://cyc.com/platform/

has more than 1000 specialized inference engines for particular kinds of problems, which doesn't seem like a terribly sustainable route.

[ssnri]

Ah, seems I was thinking of category 1b. I’ll keep reading. Great find.