Triple

T20905117
Position Surface form Disambiguated ID Type / Status
Subject The Addams Family 2 E514773 entity
Predicate productionCompany P490 FINISHED
Object Cinesite 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: Cinesite | Statement: [The Addams Family 2, productionCompany, Cinesite]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cinesite
Context triple: [The Addams Family 2, productionCompany, Cinesite]
  • A. Cinesite chosen
    Cinesite is a visual effects and animation studio known for producing and contributing to major feature films and animated projects.
  • B. Framestore
    Framestore is a leading British visual effects and animation studio renowned for its work on major feature films, television, and commercials.
  • C. Weta Digital
    Weta Digital is a renowned New Zealand-based visual effects studio best known for its groundbreaking CGI work on major films such as The Lord of the Rings trilogy, Avatar, and the Planet of the Apes series.
  • D. Scanline VFX
    Scanline VFX is a visual effects studio renowned for its cutting-edge digital effects work on major film and television productions.
  • E. DNEG Animation
    DNEG Animation is a leading global animation studio known for producing high-quality animated features and series for film and streaming platforms.
  • 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_69e0b4f8a1108190bce3d31331290ced completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6e8ff36488190987ecdfcbed4220c completed April 21, 2026, 3:03 a.m.
Created at: April 16, 2026, 12:47 p.m.