Explains the PROV-O provenance model
Entities derived from entities through activities associated with agents; a manual step such as a workbook calculation is an activity like any job (W3C PROV-O, 2013).
Can AI do this?
AI does this partly Some of the tested AI models master this; others do not show it. 2 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 100% | Mastered |
| gemini-3.5-flash-lite | Low cost | 100% | Not shown |
| gpt-6-luna | Low cost | 100% | Mastered |
| claude-haiku-5-5 | Low cost | 100% | Not shown |
Mastered means a probability of at least 90% that the model has this knobit, estimated from its graded answers. “Not shown” means the answers do not settle it either way. How the models are tested.
What it looks like in practice
Expected result: Entities derived from entities through activities associated with agents; a manual step such as a workbook calculation is an activity like any job (W3C PROV-O, 2013).
How it is assessed: Answers a written question on the provenance of data correctly
Related knobits
Needed for
- M-406 Recognises a manual-step entry nobody could find or repeat
- M-503 Recognises a manual step missing from a lineage path
- M-551 Explains data lineage as a graph of derivations
All 12 knobits of Design the metamodel.
Source: Practice the stage 2 reference and review checklist rest on