Triple

T21985094
Position Surface form Disambiguated ID Type / Status
Subject Seediq Bale E542936 entity
Predicate producer P490 FINISHED
Object ARLTA Film E542936 NE FINISHED

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: ARLTA Film | Statement: [Seediq Bale, producer, ARLTA Film]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ARLTA Film
Context triple: [Seediq Bale, producer, ARLTA Film]
  • A. ARLTA Film chosen
    ARLTA Film is a Taiwanese film production company known for producing the acclaimed historical epic "Seediq Bale."
  • B. Argus Film
    Argus Film is a film production company known for its involvement in notable European art-house cinema such as Lars von Trier’s "Breaking the Waves."
  • C. Arsenal Kino
    Arsenal Kino is a renowned Berlin art-house cinema and film archive known for its curated programs of experimental, independent, and international films.
  • D. Lippert Films
    Lippert Films was an American independent film distribution and production company active in the mid-20th century, known for handling low-budget genre movies.
  • E. Cinema Verity
    Cinema Verity was a British independent television and film production company founded by influential producer Verity Lambert, known for creating a range of acclaimed dramas and comedies.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69e0c48136b081908831fa907cc02e18 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f12708cdcc81909511d9f81bd8f20e completed April 28, 2026, 9:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a6d7d735081909b86cafe3bc85186 completed May 18, 2026, 1:38 a.m.
Created at: April 16, 2026, 8:04 p.m.