Triple

T22760823
Position Surface form Disambiguated ID Type / Status
Subject Evelyn E562980 entity
Predicate productionCompany P490 FINISHED
Object First Look Media 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: First Look Media | Statement: [Evelyn, productionCompany, First Look Media]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: First Look Media
Context triple: [Evelyn, productionCompany, First Look Media]
  • A. First Look Media chosen
    First Look Media is a media organization and news outlet known for its investigative journalism and digital publications, backed by eBay founder Pierre Omidyar.
  • B. First Look Pictures
    First Look Pictures was an independent American film distribution company known for releasing a range of arthouse, foreign, and genre films.
  • C. Outfront Media
    Outfront Media is a major American outdoor advertising company specializing in billboards, transit displays, and other out-of-home media across the United States and Canada.
  • D. Greenlight Media
    Greenlight Media is a film and television production company known for producing documentaries and feature films, including the chess documentary "Deep Blue."
  • E. Exclusive Media Group
    Exclusive Media Group is an independent film production and financing company known for backing and producing a range of high-profile feature films and documentaries.
  • 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_69e24552e11c81909c2d61578a558bd7 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17a7c45b881908b29ba1439038789 completed April 29, 2026, 3:26 a.m.
Created at: April 17, 2026, 3:26 p.m.