Triple

T19917604
Position Surface form Disambiguated ID Type / Status
Subject U.S. Triple Crown E478704 entity
Predicate firstWinner P11366 FINISHED
Object Sir Barton NE NERFINISHED

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: Sir Barton | Statement: [U.S. Triple Crown, firstWinner, Sir Barton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sir Barton
Context triple: [U.S. Triple Crown, firstWinner, Sir Barton]
  • A. Sir Barton chosen
    Sir Barton was an American Thoroughbred racehorse best known as the first winner of the U.S. Triple Crown in 1919.
  • B. Frankel
    Frankel is a legendary, unbeaten British Thoroughbred racehorse widely regarded as one of the greatest racehorses of all time.
  • C. Frankel
    Frankel is the birth surname of American actress and comedian Bea Arthur, best known for her roles in the television series "Maude" and "The Golden Girls."
  • D. Northern Dancer
    Northern Dancer was a legendary Canadian-bred Thoroughbred racehorse and stallion whose exceptional success as a sire made him one of the most influential bloodlines in modern horse racing and breeding.
  • E. Danehill
    Danehill was a champion Irish-bred Thoroughbred racehorse who became one of the most influential and successful stallions in modern breeding history.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e521855c8190b41871700afc8d6a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65995bd60819097cfad003dd29731 completed April 20, 2026, 4:51 p.m.
Created at: April 10, 2026, 1:53 p.m.