Triple

T17247907
Position Surface form Disambiguated ID Type / Status
Subject Circle of Friends E418672 entity
Predicate productionCompany P490 FINISHED
Object Savoy Pictures E1065155 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: Savoy Pictures | Statement: [Circle of Friends, productionCompany, Savoy Pictures]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Savoy Pictures
Context triple: [Circle of Friends, productionCompany, Savoy Pictures]
  • A. Savoy Pictures chosen
    Savoy Pictures was an American independent film production and distribution company active in the 1990s.
  • B. Gainsborough Pictures
    Gainsborough Pictures was a prominent British film production company active in the early to mid-20th century, known for its melodramas and for helping launch the careers of notable directors and actors.
  • C. Palace Films
    Palace Films is an Australian film distribution company known for releasing a wide range of acclaimed international and local arthouse and independent films.
  • D. Palace Pictures
    Palace Pictures was a British independent film production and distribution company known for backing influential and unconventional films in the 1980s and early 1990s.
  • E. Monarch Pictures
    Monarch Pictures is a film production company known for producing feature films such as the thriller "Copycat."
  • 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_69d886d9ab108190b70edd8d17aa1204 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42e2569c081908ffd3ee9c76bcc17 completed April 19, 2026, 1:21 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01794102348190ba5906c011fd014b completed May 11, 2026, 6:37 a.m.
Created at: April 10, 2026, 5:39 a.m.