Triple

T13610396
Position Surface form Disambiguated ID Type / Status
Subject I Smile Back E325171 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 Smile Back, productionCompany, Killer Films]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Killer Films
Context triple: [I Smile Back, 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 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.
  • D. 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.
  • 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_69d8076aae28819092cf636190ee5529 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbb0aa9a1481908c6f92495aff86c6 completed April 12, 2026, 2:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f77f9a9f9c81909b0a8f4f51c461ae completed May 3, 2026, 5:02 p.m.
Created at: April 9, 2026, 9:50 p.m.