Recognises an ambiguous pronoun in a rule statement
A pronoun with more than one possible referent. Reads fine, cannot be implemented.
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 | 75% | Not shown |
| gemini-3.1-pro-preview* | Flagship | 99% | Mastered |
| gpt-6-astra* | Flagship | 100% | Mastered |
| claude-fable-5-1* | Flagship | 99% | Mastered |
| gemini-3.8-flash* | Mid tier | 99% | Mastered |
| gpt-6.1-sol* | Mid tier | 100% | Mastered |
| claude-sonnet-5-5* | Mid tier | 99% | Mastered |
| gemini-3.5-flash-lite | Low cost | 43% | Not shown |
| gpt-6-luna | Low cost | 72% | Not shown |
| claude-haiku-5-5 | Low cost | 75% | Not shown |
* From the earlier benchmark of 2026-10: 10 data-modelling test tasks, 3 runs per task, graded by claude-opus-5-5. These models have not taken the current 123 tasks yet; the two methods differ, so compare their figures with care. They are left out of the “most models” counts and the best-model picks.
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 pronoun and its candidate referents
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: "The settled amount must not exceed the instructed amount, and it must be positive" Acceptable: "The settled amount must not exceed the instructed amount. The settled amount must be greater than zero." (RUL-020)
Also known as: Ambiguous pronoun (data rule)
Related knobits
Builds on
All 23 knobits of Document data rules in SBVR.
Source: Review checklist 02-data-rules (data-quality), row 16; formerly data-modelling K-316