Triple

T21008151
Position Surface form Disambiguated ID Type / Status
Subject Laurence Harvey E517468 entity
Predicate notableWork P4 FINISHED
Object Butterfield 8 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: Butterfield 8 | Statement: [Laurence Harvey, notableWork, Butterfield 8]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Butterfield 8
Context triple: [Laurence Harvey, notableWork, Butterfield 8]
  • A. Butterfield 8 chosen
    Butterfield 8 is a 1960 drama film starring Elizabeth Taylor as a troubled New York call girl, a role that earned her an Academy Award for Best Actress.
  • B. Last Stop Before Heaven
    "Last Stop Before Heaven" is a song by the band Intense, known for its powerful, melodic heavy metal style.
  • C. The Passenger
    "The Passenger" is a 1977 rock song by Iggy Pop, known for its driving rhythm, iconic "la-la-la" chorus, and enduring influence as one of his signature tracks.
  • D. The Passenger
    The Passenger is a late-career novel by Cormac McCarthy that follows a haunted salvage diver entangled in mystery, guilt, and philosophical inquiry in the aftermath of his sister’s suicide.
  • E. The Passenger
    "The Passenger" is a short story set in the universe of the 1995 LucasArts adventure game Full Throttle, expanding on its world of outlaw bikers and dystopian highways.
  • 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_69e0b50192308190a284fcc89dd23a49 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fc3dcb5081909b06d6db10fefba6 completed April 21, 2026, 4:25 a.m.
Created at: April 16, 2026, 1:53 p.m.