Triple

T22052076
Position Surface form Disambiguated ID Type / Status
Subject The Lost Prince E544908 entity
Predicate distributor P1951 FINISHED
Object Pathé 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: Pathé | Statement: [The Lost Prince, distributor, Pathé]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pathé
Context triple: [The Lost Prince, distributor, Pathé]
  • A. Pathé chosen
    Pathé is a historic French film production and distribution company that also operated as a major record label in the early and mid-20th century.
  • B. Pathé Industries
    Pathé Industries was an American film production and distribution company active in the mid-20th century, known for its involvement in independent and low-budget filmmaking.
  • C. Gaumont
    Gaumont is a historic French film and television production company, recognized as one of the oldest continuously operating studios in the world.
  • D. Gaumont Pathé Archives
    Gaumont Pathé Archives is a major French film and newsreel archive preserving and providing access to historical audiovisual materials from the Gaumont and Pathé studios.
  • E. Gaumont cinemas
    Gaumont cinemas is a historic French cinema chain known for operating movie theaters across France and being one of the oldest names in the film exhibition industry.
  • 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_69e11e32445c8190ab97089b48a130bb completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1285513fc8190b691e1f57085956f completed April 28, 2026, 9:36 p.m.
Created at: April 16, 2026, 8:26 p.m.