Triple

T11036351
Position Surface form Disambiguated ID Type / Status
Subject Bill Haydon E260895 entity
Predicate hasAffairWith P23617 FINISHED
Object Ann Smiley E245051 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: Ann Smiley | Statement: [Bill Haydon, hasAffairWith, Ann Smiley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ann Smiley
Context triple: [Bill Haydon, hasAffairWith, Ann Smiley]
  • A. Ann Smiley chosen
    Ann Smiley is the unfaithful and enigmatic wife of British intelligence officer George Smiley in John le Carré’s spy novels.
  • B. Virginia Weidler
    Virginia Weidler was an American child actress of the 1930s and 1940s, best remembered for her witty supporting roles in classic Hollywood films such as "The Philadelphia Story."
  • C. Ann Kirkpatrick
    Ann Kirkpatrick is an American politician and attorney best known for serving multiple terms as a U.S. Representative from Arizona.
  • D. Laura Deming
    Laura Deming is a venture capitalist and longevity researcher best known for founding The Longevity Fund, which invests in companies developing therapies to extend healthy human lifespan.
  • E. Erinn Bartlett
    Erinn Bartlett is an American actress and former beauty pageant titleholder known for supporting roles in film and television.
  • 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_69d6aa979bdc8190bf0e79104cc098c1 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d797e9e3fc8190802195ac9fcb8e28 completed April 9, 2026, 12:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3a9b70074819084c725c5babf2fb7 completed April 18, 2026, 3:56 p.m.
Created at: April 8, 2026, 9:25 p.m.