Triple

T23231114
Position Surface form Disambiguated ID Type / Status
Subject Hunger (1966 film) E581155 entity
Predicate productionCompany P490 FINISHED
Object Norsk Film 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: Norsk Film | Statement: [Hunger (1966 film), productionCompany, Norsk Film]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Norsk Film
Context triple: [Hunger (1966 film), productionCompany, Norsk Film]
  • A. Norsk Film chosen
    Norsk Film was a major Norwegian film production company that played a central role in the country’s cinema industry throughout much of the 20th century.
  • B. Norwegian Film Institute
    The Norwegian Film Institute is Norway’s national agency responsible for supporting, promoting, and preserving Norwegian cinema and film culture.
  • C. Nordisk Film
    Nordisk Film is a major Danish entertainment company and one of the world’s oldest film studios, known for producing and distributing films across the Nordic region.
  • D. Norwegian cinema network
    The Norwegian cinema network is a nationwide chain of movie theaters in Norway that operates and coordinates cinemas such as Colosseum kino.
  • E. Svensk Filmindustri
    Svensk Filmindustri is a major Swedish film production and distribution company, historically one of the country’s most influential studios.
  • 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_69e246043c48819089bae72c9a9c306c completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f19231ef908190a791b4967916a66f completed April 29, 2026, 5:08 a.m.
Created at: April 17, 2026, 4:09 p.m.