Triple

T13580824
Position Surface form Disambiguated ID Type / Status
Subject Doug Wright E324411 entity
Predicate notableWork P4 FINISHED
Object Quills E62118 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: Quills | Statement: [Doug Wright, notableWork, Quills]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Quills
Context triple: [Doug Wright, notableWork, Quills]
  • A. Quills chosen
    Quills is a 2000 period drama film that fictionalizes the final years of the Marquis de Sade, featuring Geoffrey Rush in a critically acclaimed leading role.
  • B. Logorama
    Logorama is a 2009 French animated short film that satirically depicts a world made entirely of corporate logos and mascots.
  • C. L’Incorruptible
    L’Incorruptible is the famous sobriquet of Maximilien Robespierre, the influential and controversial leader of the French Revolution’s radical phase and the Reign of Terror.
  • D. Certified Copy
    Certified Copy is a 2010 art-house drama film directed by Abbas Kiarostami, featuring Juliette Binoche as a woman whose ambiguous relationship with a writer blurs the line between reality and performance.
  • E. Finding Forrester
    Finding Forrester is a 2000 drama film about a reclusive writer who mentors a gifted young student, directed by Gus Van Sant.
  • 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_69d80769100c819099111274614f5ed2 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbb03052088190a2b68c106059828e completed April 12, 2026, 2:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69f78ae008788190b3ebc09e73ec4952 completed May 3, 2026, 5:50 p.m.
Created at: April 9, 2026, 9:48 p.m.