Recognises a general concept tied to one subject field
A general concept is defined as if it existed in one field only, which blocks reuse and causes duplicate definitions. If the meaning really is field-specific, mark the field, e.g. <banking>.
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 | 82% | Not shown |
| gemini-3.5-flash-lite | Low cost | 5% | Not shown |
| gpt-6-luna | Low cost | 5% | Not shown |
| claude-haiku-5-5 | Low cost | 82% | 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 field restriction and whether to drop or mark it
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: maturity date: date on which a bank loan must be repaid in full (in a glossary that also covers bonds and deposits) Acceptable: maturity date: date on which the principal of a financial instrument becomes due for payment
Also known as: Wrongly tied to one subject field (business term)
Related knobits
Builds on
All 18 knobits of Define business terms in the glossary.
Source: Review checklist 03-business-glossary (metadata-management), row 6; formerly data-modelling K-206