Triple

T15261163
Position Surface form Disambiguated ID Type / Status
Subject Altior E364777 entity
Predicate trainedBy P3665 FINISHED
Object Nicky Henderson E1151628 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: Nicky Henderson | Statement: [Altior, trainedBy, Nicky Henderson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nicky Henderson
Context triple: [Altior, trainedBy, Nicky Henderson]
  • A. Nicky Henderson chosen
    Nicky Henderson is a leading British National Hunt racehorse trainer renowned for handling numerous top-class jumpers and multiple Cheltenham Festival winners.
  • B. Paul Nicholls
    Paul Nicholls is a leading British National Hunt racehorse trainer renowned for handling multiple champion jumpers, including the legendary Kauto Star.
  • C. Gordon Elliott
    Gordon Elliott is an Australian-born television personality and producer best known for hosting various American talk and game shows.
  • D. Bill Mott
    Bill Mott is a Hall of Fame American Thoroughbred racehorse trainer best known for conditioning champions such as the legendary racehorse Cigar.
  • E. Gary Stevens (jockey)
    Gary Stevens is a Hall of Fame American jockey and horse racing analyst renowned for winning multiple Kentucky Derbies, Preakness Stakes, and Breeders’ Cup races over a decades-long career.
  • 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_69d85a0f08408190b3c3259ae35d79d2 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0084e85a08190b8e63598b9f6a535 completed April 15, 2026, 9:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69ff0b39b6f88190ac9d6532e99fda31 completed May 9, 2026, 10:23 a.m.
Created at: April 10, 2026, 3:14 a.m.