Triple

T19983360
Position Surface form Disambiguated ID Type / Status
Subject BFI London Film Festival E493870 entity
Predicate hasAward P219 FINISHED
Object Audience Award 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: Audience Award | Statement: [BFI London Film Festival, hasAward, Audience Award]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Audience Award
Context triple: [BFI London Film Festival, hasAward, Audience Award]
  • A. Audience Award
    The Audience Award is a prize at the Turin Film Festival determined by the votes of festival attendees, recognizing the most popular film among viewers.
  • B. Audience Award chosen
    The Audience Award is a prize at the BFI London Film Festival voted on by festival attendees to recognize the most popular film.
  • C. Audience Award
    The Audience Award is a prize at the Thessaloniki International Film Festival given to the film most favored by festival attendees.
  • D. Audience Award
    The Audience Award is a prize at the San Francisco International Film Festival given to films that receive the highest approval from festival attendees.
  • E. Audience Award
    The Audience Award is a prize at the Tallinn Black Nights Film Festival given to the film that receives the highest approval from festival attendees.
  • 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_69da626a67648190af9653832a3aeced completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65d14c3c08190b1ba8f4da08a4ccf completed April 20, 2026, 5:06 p.m.
Created at: April 11, 2026, 3:28 p.m.