Triple

T5756836
Position Surface form Disambiguated ID Type / Status
Subject Stephen Ward E126987 entity
Predicate hasFriend P8712 FINISHED
Object Christine Keeler E127967 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: Christine Keeler | Statement: [Stephen Ward, hasFriend, Christine Keeler]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Christine Keeler
Context triple: [Stephen Ward, hasFriend, Christine Keeler]
  • A. Christine Keeler chosen
    Christine Keeler was a British model and showgirl whose involvement with government minister John Profumo in the early 1960s sparked the Profumo affair, a major political scandal in the United Kingdom.
  • B. Martha Profumo
    Martha Profumo was the mother of British politician John Profumo, who became widely known for the 1963 Profumo affair scandal.
  • C. Adrienne Ames
    Adrienne Ames was an American film actress of the 1930s known for her glamorous screen presence and roles in Hollywood dramas and comedies.
  • D. Christina Crawford
    Christina Crawford is an American author and actress best known for her memoir "Mommie Dearest," which exposed the alleged abusive behavior of her adoptive mother, Hollywood star Joan Crawford.
  • E. Janet Hill
    Janet Hill is known as the former wife of Apple co-founder Steve Wozniak.
  • 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_69c00833a3fc81908f4bc29ed011b7a6 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c029084e108190988f1b5f38254007 completed March 22, 2026, 5:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0a16b9eac8190a3760557e2aebb45 completed March 23, 2026, 2:11 a.m.
Created at: March 22, 2026, 3:49 p.m.