Triple

T14521010
Position Surface form Disambiguated ID Type / Status
Subject I'm Not There E340649 entity
Predicate productionCompany P490 FINISHED
Object Killer Films E98620 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: Killer Films | Statement: [I'm Not There, productionCompany, Killer Films]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Killer Films
Context triple: [I'm Not There, productionCompany, Killer Films]
  • A. Killer Films chosen
    Killer Films is an independent American film production company known for producing critically acclaimed, often unconventional and auteur-driven movies.
  • B. Killer
    Killer is the nickname of Harmon Killebrew, a Hall of Fame Major League Baseball slugger renowned for his prodigious home run power, primarily with the Minnesota Twins.
  • C. Killer
    "Killer" is a 1990 dance track by British producer Adamski, best known for its distinctive house beat and Seal's uncredited vocals, which became a major hit in the UK and Europe.
  • D. Killer
    Killer is the nickname of Doug Gilmour, a Hall of Fame Canadian ice hockey player renowned for his gritty two-way play and leadership in the NHL.
  • E. Ladykiller
    "Ladykiller" is a moody, soulful rock song by The Horrible Crowes, the side project of The Gaslight Anthem’s Brian Fallon.
  • 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_69d822d9c0408190b9a2b3643e58bb4d completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69de9a72cff08190878b4bed9b0b5eb5 completed April 14, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd7a4da6908190a3e2cae16f6240d9 completed May 8, 2026, 5:53 a.m.
Created at: April 10, 2026, 1:22 a.m.