Triple

T23475901
Position Surface form Disambiguated ID Type / Status
Subject Irish Grand National E570261 entity
Predicate notableWinner P2766 FINISHED
Object Arkle 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: Arkle | Statement: [Irish Grand National, notableWinner, Arkle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arkle
Context triple: [Irish Grand National, notableWinner, Arkle]
  • A. Arkle chosen
    Arkle was a legendary Irish Thoroughbred racehorse widely regarded as one of the greatest steeplechasers in the history of National Hunt racing.
  • B. Richard Goulding
    Richard Goulding is a British actor known for his work in television, film, and theatre, including prominent roles in political and historical dramas.
  • C. Larkin Arnold
    Larkin Arnold is a prominent American music and entertainment executive known for signing and developing major recording artists and producing influential projects in the industry.
  • D. Thomas Holy Suckley
    Thomas Holy Suckley was a 19th-century member of a prominent New York family who originally owned the estate now preserved as the Wilderstein Historic Site in Rhinebeck, New York.
  • E. Ernest Haycox
    Ernest Haycox was an American author renowned for his prolific and influential Western fiction, several of whose stories were adapted into classic Hollywood films.
  • 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_69e245af8a88819084f2704f6d265a92 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a74cf57081909d2b90a806d68c08 completed April 29, 2026, 6:38 a.m.
Created at: April 17, 2026, 6:01 p.m.