Triple

T17802527
Position Surface form Disambiguated ID Type / Status
Subject Rochelle Humes E444466 entity
Predicate presentedWith P4540 FINISHED
Object Vernon Kay 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: Vernon Kay | Statement: [Rochelle Humes, presentedWith, Vernon Kay]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vernon Kay
Context triple: [Rochelle Humes, presentedWith, Vernon Kay]
  • A. Vernon Kay chosen
    Vernon Kay is a British television and radio presenter known for hosting shows such as "All Star Family Fortunes" and various programs on BBC Radio.
  • B. Vernon Green
    Vernon Green was an American R&B singer and songwriter best known as the lead vocalist of the 1950s doo-wop group The Medallions.
  • C. Eric Gairy
    Eric Gairy was a Grenadian politician and trade union leader who served as the country’s first prime minister and was later overthrown in a 1979 coup.
  • D. Roy Bland
    Roy Bland is a fictional British intelligence officer and double agent in John le Carré’s George Smiley novels, notably featured as one of the suspected moles in "Tinker Tailor Soldier Spy."
  • E. Gordon Heath
    Gordon Heath was an American actor, singer, and director known for his work on stage and in film, as well as for his influential career in Europe, particularly in France.
  • 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_69d8b9efe370819095cd219b143ae727 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e488005a288190b7a2cffa590d2557 completed April 19, 2026, 7:45 a.m.
Created at: April 10, 2026, 10:13 a.m.