Triple

T15860352
Position Surface form Disambiguated ID Type / Status
Subject Chantilly, France E384565 entity
Predicate hasEvent P811 FINISHED
Object Prix de Diane E1066887 NE 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: Prix de Diane | Statement: [Chantilly, France, hasEvent, Prix de Diane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Prix de Diane
Context triple: [Chantilly, France, hasEvent, Prix de Diane]
  • A. Prix de Diane chosen
    The Prix de Diane is a prestigious French Group 1 flat horse race for three-year-old fillies, often regarded as the French equivalent of the Oaks.
  • B. Prix de la Reine Blanche
    The Prix de la Reine Blanche is a French thoroughbred horse race held at Chantilly Racecourse, typically featuring flat racing over a middle distance.
  • C. Prix de la Reine Marguerite
    The Prix de la Reine Marguerite is a French Thoroughbred horse race held at Chantilly Racecourse, typically contested by stayers over a long distance on turf.
  • D. Prix de Paris
    The Prix de Paris is a prestigious long-distance Group 1 harness race in French trotting, regarded as one of the key events of the winter meeting in Paris.
  • E. Prix de Flore
    The Prix de Flore is a French Group 3 flat horse race for thoroughbred fillies and mares, typically run over a middle distance in the autumn.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d86da422088190aac39e32e6c68429 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1555a1f008190bb3f03b0f35ed8a4 completed April 16, 2026, 9:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffa14da7ac8190bbef49a1602a76fe completed May 9, 2026, 9:04 p.m.
Created at: April 10, 2026, 4:50 a.m.