Recognises business meaning stored on a technical metadata class
A column class carrying its own business definition instead of a link to a term.
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 | 90% | Not shown |
| gemini-3.5-flash-lite | Low cost | 10% | Not shown |
| gpt-6-luna | Low cost | 10% | Not shown |
| claude-haiku-5-5 | Low cost | 10% | 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: The link from the column class to the business term class
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: MC-005 Column has business_definition, curated in the catalogue Acceptable: MC-005 links to MC-001 (ML-001 column represents term)
Also known as: Business meaning stored on the technical class
Related knobits
Builds on
All 12 knobits of Design the metamodel.
Source: Review checklist 02-metamodel, row 5 (11179-3 (data element represents a data element concept))