Triple

T15045430
Position Surface form Disambiguated ID Type / Status
Subject Disclosure E379213 entity
Predicate EP P15272 FINISHED
Object The Face E835923 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: The Face | Statement: [Disclosure, EP, The Face]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: The Face
Context triple: [Disclosure, EP, The Face]
  • A. The Face chosen
    "The Face" is a song by British rock band Kings of Leon from their 2010 album *Come Around Sundown*.
  • B. A Face
    "A Face" is a poem by Robert Browning that explores themes of beauty, perception, and the emotional power conveyed through a human face.
  • C. Here a Face, There a Face
    "Here a Face, There a Face" is a children's picture book by photographer and author Arlene Alda that invites young readers to discover faces in everyday objects and surroundings.
  • D. "Faces"
    "Faces" is an episode of Star Trek: Voyager in which B'Elanna Torres is split into separate human and Klingon versions of herself by the organ-harvesting Vidiian race.
  • E. The Face That Must Die
    The Face That Must Die is a psychological horror novel by British author Ramsey Campbell, focusing on a paranoid, violent man whose delusions drive him toward murder in a grimly realistic urban setting.
  • 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_69d85cd64d108190853797a95c11cc45 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded830c3c08190a87b81abbbb75377 completed April 15, 2026, 12:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe9de54380819084568664b63322d2 completed May 9, 2026, 2:37 a.m.
Created at: April 10, 2026, 3 a.m.