Triple

T15260710
Position Surface form Disambiguated ID Type / Status
Subject Bet365 E364765 entity
Predicate hasKeyPerson P256 FINISHED
Object John Coates E1146564 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: John Coates | Statement: [Bet365, hasKeyPerson, John Coates]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Coates
Context triple: [Bet365, hasKeyPerson, John Coates]
  • A. John Coates
    John Coates was a prominent Australian mathematician known for his influential work in number theory, particularly Iwasawa theory, and for mentoring leading mathematicians including Andrew Wiles.
  • B. John Coates chosen
    John Coates is a British businessman best known as the co-CEO of online gambling giant Bet365, which he co-founded with his sister Denise Coates.
  • C. Anthony Wood
    Anthony Wood is a central character in the 1973 mystery film "The Last of Sheila," involved in a complex whodunit plot surrounding a deadly yacht party game.
  • D. Anthony Wood
    Anthony Wood was a 17th-century English antiquary and historian best known for his detailed works on the history and biography of the University of Oxford.
  • E. Anthony Wood
    Anthony Wood is a technology entrepreneur best known as the founder and CEO of Roku, a leading streaming media platform.
  • 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_69feef6def4c8190b6aed1f68d336c5a completed May 9, 2026, 8:25 a.m.
Created at: April 10, 2026, 3:14 a.m.