Triple

T17990832
Position Surface form Disambiguated ID Type / Status
Subject Flickering Lights E430364 entity
Predicate distributor P1951 FINISHED
Object Nordisk 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: Nordisk Film | Statement: [Flickering Lights, distributor, Nordisk Film]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nordisk Film
Context triple: [Flickering Lights, distributor, Nordisk Film]
  • A. Nordisk Film chosen
    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.
  • B. Svensk Filmindustri
    Svensk Filmindustri is a major Swedish film production and distribution company, historically one of the country’s most influential studios.
  • C. Norsk Film
    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.
  • D. Danish Film Institute
    The Danish Film Institute is Denmark’s national agency for film and cinema, responsible for supporting, promoting, and preserving Danish film culture and industry.
  • E. Astra Film Company
    Astra Film Company was an early 20th-century American silent film production studio known for its popular serials and melodramas.
  • 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_69d8b90364248190a37381adea932f42 completed April 10, 2026, 8:46 a.m.
NER Named-entity recognition batch_69e4b29f127c81908b0c4cb3787e002c completed April 19, 2026, 10:46 a.m.
Created at: April 10, 2026, 10:23 a.m.