Explains metadata for big data ingest
Technical, operational and profiling metadata captured when data lands in a lake, with tags and lineage, so that data read by schema-on-read can still be found and trusted.
Can AI do this?
People still lead Few or none of the tested AI models showed they master this. 0 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 58% | Not shown |
| gemini-3.5-flash-lite | Low cost | 49% | Not shown |
| gpt-6-luna | Low cost | 58% | Not shown |
| claude-haiku-5-5 | Low cost | 58% | 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: Technical, operational and profiling metadata captured when data lands in a lake, with tags and lineage, so that data read by schema-on-read can still be found and trusted.
How it is assessed: Answers a CDMP-style multiple-choice question on the metadata at data lake ingest
All knobits of Metadata management.
Source: DAMA-DMBOK: Data Management Body of Knowledge, 2nd edition (revised), chapter 12: Metadata Management, element MV-21