Triple

T19547390
Position Surface form Disambiguated ID Type / Status
Subject Lionel White E489109 entity
Predicate notableWork P4 FINISHED
Object Obsession 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: Obsession | Statement: [Lionel White, notableWork, Obsession]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Obsession
Context triple: [Lionel White, notableWork, Obsession]
  • A. Obsession
    Obsession is a pop and R&B studio album by English singer Shayne Ward, showcasing his smooth vocals and contemporary ballads.
  • B. Obsession
    "Obsession" is a synth-pop single by American singer Sky Ferreira that helped introduce her dark, edgy pop aesthetic to a wider audience.
  • C. Obsession
    Obsession is a 1976 psychological thriller film directed by Brian De Palma, known for its Hitchcockian style, themes of guilt and identity, and Bernard Herrmann’s haunting score.
  • D. Obsession chosen
    Obsession is a novel by American crime writer Lionel White, known for its hardboiled suspense and for inspiring Jean-Luc Godard’s film "Pierrot le Fou."
  • E. Obsession
    Obsession is a psychological horror novel by British writer Ramsey Campbell, centered on childhood guilt, dark secrets, and the haunting consequences of past actions.
  • 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_69d8e8db5b6c8190984b61f91981f575 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63d2d8a6081908e9bb3a6f5d85896 completed April 20, 2026, 2:50 p.m.
Created at: April 10, 2026, 1:41 p.m.