Triple

T6700270
Position Surface form Disambiguated ID Type / Status
Subject Julie Delpy E152859 entity
Predicate starredIn P1668 FINISHED
Object Killing Zoe E492790 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: Killing Zoe | Statement: [Julie Delpy, starredIn, Killing Zoe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Killing Zoe
Context triple: [Julie Delpy, starredIn, Killing Zoe]
  • A. Killing Zoe chosen
    Killing Zoe is a 1993 independent crime thriller film about a high-stakes bank heist in Paris that spirals into violence and chaos.
  • B. Seven Days to a Killing
    Seven Days to a Killing is a 1972 spy thriller novel by Clive Egleton, centered on a British intelligence officer whose son is kidnapped as part of a high-stakes blackmail plot.
  • C. They Keep Killing Suzie
    "They Keep Killing Suzie" is a darkly comedic and emotionally intense episode of the British sci-fi series Torchwood that explores resurrection technology and its psychological consequences.
  • D. Great Kills
    Great Kills is a residential neighborhood on Staten Island’s South Shore known for its marina, waterfront parks, and suburban character.
  • E. A Vow to Kill
    A Vow to Kill is a 1995 made-for-television thriller film starring Julianne Phillips as a woman whose seemingly perfect marriage turns dangerously deadly.
  • 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_69c68807adbc8190b8632df42b39eda0 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d0a7355081908a0acfa8d2bb4c09 completed March 27, 2026, 6:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6f7c127288190a9917f482217a8df completed March 27, 2026, 9:33 p.m.
Created at: March 27, 2026, 2:05 p.m.