Triple

T13945308
Position Surface form Disambiguated ID Type / Status
Subject Anouk Aimée E335364 entity
Predicate notableWork P4 FINISHED
Object Justine E249269 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: Justine | Statement: [Anouk Aimée, notableWork, Justine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Justine
Context triple: [Anouk Aimée, notableWork, Justine]
  • A. Justine
    Justine is the naive college student protagonist who joins an activist trip to the Amazon that turns into a brutal fight for survival in the horror film "The Green Inferno."
  • B. Justine chosen
    Justine is a film featuring actress and singer Romina Power, known as one of her notable screen roles.
  • C. Justine
    Justine is a character from the 1960 horror film "The Hypnotic Eye," involved in the movie’s sinister plot centered on mind control and mysterious disfigurements.
  • D. Justine
    Justine is a given name commonly used for women in various cultures, derived from the Latin name Justina meaning "just" or "righteous."
  • E. Justine Moritz
    Justine Moritz is a gentle, devout young woman in Mary Shelley's "Frankenstein" who becomes a tragic victim of injustice when she is wrongfully executed for a murder committed by Victor Frankenstein's creature.
  • 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_69d81c6081b88190b53e317c3370c8fe completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2e10f60c81908ee9636e85c070ff completed April 14, 2026, 12:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7ce8da5908190aab069dc9b74b083 completed May 3, 2026, 10:39 p.m.
Created at: April 9, 2026, 10:17 p.m.