Triple

T17265618
Position Surface form Disambiguated ID Type / Status
Subject Marla Singer E419118 entity
Predicate associatedWith P37 FINISHED
Object Tyler Durden E318162 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: Tyler Durden | Statement: [Marla Singer, associatedWith, Tyler Durden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tyler Durden
Context triple: [Marla Singer, associatedWith, Tyler Durden]
  • A. Tyler Durden chosen
    Tyler Durden is the anarchic, charismatic alter ego of the unnamed narrator in "Fight Club," embodying his repressed desires for rebellion, violence, and anti-consumerist freedom.
  • B. Eric Draven
    Eric Draven is the vengeful, resurrected rock musician and antihero from the dark fantasy film and comic series "The Crow."
  • C. Robert Gantz
    Robert Gantz is a film cinematographer known for his work on the thriller "Mindhunters."
  • D. Jack Endino
    Jack Endino is an American record producer, engineer, and musician best known for shaping the early Seattle grunge sound through his work with bands like Nirvana and Soundgarden.
  • E. Steven Kyle
    Steven Kyle is best known as the husband of acclaimed American lyricist and screenwriter Betty Comden.
  • 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_69d886d9ab108190b70edd8d17aa1204 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42f44ec7c81909a925fc8692b0a6c completed April 19, 2026, 1:26 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01794641648190a5db87ecb359c17a completed May 11, 2026, 6:37 a.m.
Created at: April 10, 2026, 5:40 a.m.