Triple

T8329528
Position Surface form Disambiguated ID Type / Status
Subject A Double Life E195039 entity
Predicate stars P1956 FINISHED
Object Ray Collins E108489 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: Ray Collins | Statement: [A Double Life, stars, Ray Collins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ray Collins
Context triple: [A Double Life, stars, Ray Collins]
  • A. Ray Collins chosen
    Ray Collins was an American character actor best known for his roles in classic films and radio, including his appearance in Orson Welles’s landmark film "Citizen Kane."
  • B. Alan Collins
    Alan Collins was a British-born sculptor known for his modernist religious and commemorative works, including prominent public memorials in the United States and the United Kingdom.
  • C. Colin Blakely
    Colin Blakely was a Northern Irish character actor known for his powerful stage work and memorable supporting roles in British and international films of the 1960s–1980s.
  • D. Phil Collinson
    Phil Collinson is a British television producer best known for his work on the revived era of Doctor Who.
  • E. Mo Collins
    Mo Collins is an American actress and comedian best known for her sketch comedy work and memorable characters on the television series MADtv.
  • 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_69ca82e87f2c8190bdb71ee29dfc642d completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7fb812508190aed8a283dacf712e completed March 31, 2026, 8:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd95c2c36481909793e9cd0c28168a completed April 1, 2026, 10:01 p.m.
Created at: March 30, 2026, 5:56 p.m.