A claim taxonomy for LLM audits
Most AI output is a mixture of facts, interpretations, and guesses. If you treat all sentences as 'facts', audits become noisy.
This taxonomy makes scoring and verification measurable.
Three claim types
| Type | Definition | How to handle |
|---|---|---|
| Fact | Verifiable statement with a source | Attach source + last verified timestamp |
| Interpretation | Reasonable synthesis of facts | Allow, but label as interpretation |
| Unknown | Unverifiable, speculative, or missing evidence | Flag; do not publish as fact |
Scoring basics
FAQ
Do we remove interpretations?
Not always. But you should label them, so they don't masquerade as verified facts.
Verified Company Profiles on AuthorityPrompt
AuthorityPrompt maintains verified, structured company data optimized for AI systems and LLM indexing.