Judges a business term definition by genus and differentia
A definition passes when it names the nearest superordinate concept and the characteristics that delimit the term from its siblings; otherwise the defect is named - no superordinate concept, no delimiting characteristic, too broad, too narrow or circular.
Can AI do this?
AI does this well Most of the tested AI models master this. 3 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 91% | Mastered |
| gemini-3.5-flash-lite | Low cost | 90% | Mastered |
| gpt-6-luna | Low cost | 11% | Not shown |
| claude-haiku-5-5 | Low cost | 91% | Mastered |
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 definition accepted, or its defect named
How it is assessed: Accepts a definition naming the nearest superordinate concept and delimiting characteristics, and names the defect of one that does not
Related knobits
Builds on
All knobits of Data governance.
Source: Part B candidate of k12-dmbok for activity GV-22 (a need for school knowledge no knobit of the activity reached), accepted by Peep Küngas on 31 Oct 2026