Triple

T21229885
Position Surface form Disambiguated ID Type / Status
Subject The Boat Is Full E523178 entity
Predicate distributor P1951 FINISHED
Object Filmcooperative Zürich 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: Filmcooperative Zürich | Statement: [The Boat Is Full, distributor, Filmcooperative Zürich]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Filmcooperative Zürich
Context triple: [The Boat Is Full, distributor, Filmcooperative Zürich]
  • A. Filmcooperative Zürich chosen
    Filmcooperative Zürich is a Swiss film distribution collective known for handling the release of independent and art-house films.
  • B. Studio Suisse
    Studio Suisse is an art school historically known for its role in the 19th-century Parisian art scene under the name Académie Suisse, where many notable artists informally trained.
  • C. Coop (Switzerland)
    Coop (Switzerland) is one of the largest Swiss retail and wholesale cooperatives, operating supermarkets, department stores, and various service businesses across the country.
  • D. SP Zürich
    SP Zürich is the cantonal branch of Switzerland’s Social Democratic Party operating in the Canton of Zurich.
  • E. Swissbau
    Swissbau is a major Swiss trade fair and exhibition platform focused on the construction, real estate, and architecture sectors.
  • 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_69e0b512ad94819087942b2ed925185f completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e734ae60408190a9480b27d109b8fc completed April 21, 2026, 8:26 a.m.
Created at: April 16, 2026, 3:45 p.m.