Triple

T8389927
Position Surface form Disambiguated ID Type / Status
Subject Mike Flanagan E197914 entity
Predicate directorOf P537 FINISHED
Object Absentia E730772 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: Absentia | Statement: [Mike Flanagan, directorOf, Absentia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Absentia
Context triple: [Mike Flanagan, directorOf, Absentia]
  • A. Absentia chosen
    Absentia is a low-budget 2011 psychological horror film written and directed by Mike Flanagan that explores grief and supernatural terror surrounding a mysterious tunnel.
  • B. In Absentia
    In Absentia is a contemporary art work by Canadian painter Wanda Koop, reflecting her signature exploration of landscape, memory, and perception.
  • C. Absence (album)
    Absence is a jazz album by trumpeter and composer Terence Blanchard that showcases his modern, cinematic approach to jazz and improvisation.
  • D. We Die Alone
    We Die Alone is a World War II survival memoir by David Howarth that recounts the harrowing escape of Norwegian commando Jan Baalsrud through Arctic Norway after a failed sabotage mission.
  • E. Living in Oblivion
    Living in Oblivion is a 1995 independent dark comedy film that satirizes the chaos and frustrations of low-budget movie-making.
  • 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_69ca82f749388190bffbea6dfb509016 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb810ac380819095bd67f0555ac2a8 completed March 31, 2026, 8:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69ce02cb3a1481908d30993d47c70039 completed April 2, 2026, 5:46 a.m.
Created at: March 30, 2026, 6:03 p.m.