Triple

T15355250
Position Surface form Disambiguated ID Type / Status
Subject Office Space E367154 entity
Predicate portrayedBy P1507 FINISHED
Object David Herman E818789 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: David Herman | Statement: [Office Space, portrayedBy, David Herman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Herman
Context triple: [Office Space, portrayedBy, David Herman]
  • A. David Herman chosen
    David Herman is an American actor and comedian best known as an original cast member of MADtv and for his voice work on the animated series King of the Hill.
  • B. David Resnik
    David Resnik is an American bioethicist known for his work on research ethics, scientific integrity, and the ethical implications of environmental and public health policy.
  • C. David Gamson
    David Gamson is an American songwriter, producer, and musician best known for his work with the band Scritti Politti and for co-writing major pop hits for artists like Kelly Clarkson.
  • D. Brad Dechter
    Brad Dechter is an American orchestrator and arranger known for his work on numerous film scores, including major animated features.
  • E. David T. Wagner
    David T. Wagner is a screenwriter best known for co-writing the college comedy film "Van Wilder."
  • 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_69d85a1483788190ad93c2748e8af34b completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e2c00648190ae2325e1ee58dcfd completed April 16, 2026, 1:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff02012fa48190a108f1ca710ffb15 completed May 9, 2026, 9:44 a.m.
Created at: April 10, 2026, 3:18 a.m.