Triple

T10845016
Position Surface form Disambiguated ID Type / Status
Subject Barry Otto E255986 entity
Predicate spouse P13 FINISHED
Object Susan Hill E701504 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: Susan Hill | Statement: [Barry Otto, spouse, Susan Hill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susan Hill
Context triple: [Barry Otto, spouse, Susan Hill]
  • A. Susan Hill chosen
    Susan Hill is a British author best known for her ghost stories and novels, including the modern classic "The Woman in Black."
  • B. Ruth Rendell
    Ruth Rendell was a renowned British crime writer best known for her Inspector Wexford novels and psychologically complex thrillers.
  • C. Val McDermid
    Val McDermid is a Scottish crime writer renowned for her psychological thrillers and influential contributions to contemporary crime fiction.
  • D. Vera West
    Vera West was an American costume designer best known for her work on numerous Universal Pictures films in the 1930s and 1940s, particularly in the horror and melodrama genres.
  • E. P. D. James
    P. D. James was a renowned British crime novelist best known for her Adam Dalgliesh detective series and her sophisticated, psychologically rich mysteries.
  • 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_69d6aa81a5d08190aa86689061d1ddd2 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d750d0155c81908fb55ba6b45db800 completed April 9, 2026, 7:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69deb162d718819081fbc3a082672b4f completed April 14, 2026, 9:28 p.m.
Created at: April 8, 2026, 9:19 p.m.