Triple
T34818210
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Échelle des Crus |
E1003694
|
entity |
| Predicate | PremierCruThresholdRange |
P149133
|
FINISHED |
| Object | 90–99 percent |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: 90–99 percent | Statement: [Échelle des Crus, PremierCruThresholdRange, 90–99 percent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: PremierCruThresholdRange Context triple: [Échelle des Crus, PremierCruThresholdRange, 90–99 percent]
-
A.
tierRange
Indicates that one entity specifies the minimum and maximum tier levels within which another entity falls or is applicable.
-
B.
isPremierTierOf
Indicates that one entity is the highest or most elite tier or level within the hierarchical structure of another entity.
-
C.
offersGradeRange
Indicates that an entity provides educational instruction or services spanning a specified range of grade levels.
-
D.
primaryScoringRange
chosen
Indicates the main numerical interval or category within which an entity’s score or rating is evaluated or classified.
-
E.
accelerationThreshold
Indicates a condition where an entity’s acceleration reaches or exceeds a specified limit that triggers a particular response or state.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f76db717088190811b4e744610f37d |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f77abaa8008190bd81a42b0b0b055f |
completed | May 3, 2026, 4:41 p.m. |
| PD | Predicate disambiguation | batch_69f7795b1abc8190823664d1caa94649 |
completed | May 3, 2026, 4:35 p.m. |
Created at: May 3, 2026, 4 p.m.