Explains identifiers for deterministic matching
An exact-match key must be unique per person and present in the sources compared (ISO 8000-115); shared e-mail addresses and phones are not identifiers.
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 | 100% | Mastered |
| gemini-3.5-flash-lite | Low cost | 88% | Not shown |
| gpt-6-luna | Low cost | 100% | Mastered |
| claude-haiku-5-5 | Low cost | 100% | 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: An exact-match key must be unique per person and present in the sources compared (ISO 8000-115); shared e-mail addresses and phones are not identifiers.
How it is assessed: Answers a written question on the matching identifiers correctly
Related knobits
Needed for
- R-301 Recognises a deterministic match key several people share
- R-307 Recognises a match rule on a field a source lacks
- R-333 Decides record pairs without false merges
- R-334 Uses only identifiers the sources hold
All 16 knobits of Define the matching rules.
Source: Practice the stage 3 reference and review checklist rest on