[evanjrowley]

The markup in this case would be some type of semantic web format, like JSON-LD[0] or OWL[1], or some database that can process SPARQL[2] queries. Goal being the "inverse" of something like OWL2Vec[2].

EDIT1: A few weeks ago, a team of Brazilian researchers published a report about using ChatGPT to enhance agriculture-focused OWL dataset[4].

EDIT2: In addition to training LLMs on ontologies, it looks like Palantir is using ontologies as guardrails to prevent LLM hallucinations[5]. Makes sense.

[0] https://json-ld.org/

[1] https://www.w3.org/TR/owl2-syntax/

[2] https://www.w3.org/TR/sparql11-query/

[3] https://arxiv.org/abs/2009.14654

[4] https://arxiv.org/abs/2504.18651

[5] https://blog.palantir.com/reducing-hallucinations-with-the-o...