I bet one person could probably build a pretty good synthetic NL->Prolog dataset. ROI for paying that person would be high if you were building a foundation model (ie benefits beyond being able to output Prolog.)
I'm not exactly sure what you're referring to, but Fernando Pereira's dissertation included a natural language (English) program for querying a "database". Both the NLP part and the database were written in Prolog. Mid-1980s, I think. Of course both parts were "toy" in the sense that they would need to be hugely expanded to be of real world use, but they did handle some interesting things (like quantifiers, graded adjectives etc.).