Triple

T7330094
Position Surface form Disambiguated ID Type / Status
Subject The True Cost E168976 entity
Predicate producer P490 FINISHED
Object Andrew Morgan E664698 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: Andrew Morgan | Statement: [The True Cost, producer, Andrew Morgan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andrew Morgan
Context triple: [The True Cost, producer, Andrew Morgan]
  • A. Andrew Morgan chosen
    Andrew Morgan is a filmmaker best known for directing the documentary "The True Cost," which examines the global impact of the fast fashion industry.
  • B. Mark Brazill
    Mark Brazill is an American television writer and producer best known for co-creating the hit sitcom That '70s Show.
  • C. Michael Leahy
    Michael Leahy is a relatively common personal name shared by multiple individuals, including figures in politics, sports, and academia.
  • D. Andrew Gunn
    Andrew Gunn is an American film producer known for his work on family-oriented and teen-focused movies, including several popular Disney films.
  • E. Ian Bryce
    Ian Bryce is a British film producer known for his work on major Hollywood blockbusters such as Saving Private Ryan and the Transformers series.
  • 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_69c68a568a6481908f11e20db7bc8446 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f0ab0b1881909f8f086b81fdddb7 completed March 27, 2026, 9:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69c83433ca8081909ab00d1fe3ab1041 completed March 28, 2026, 8:04 p.m.
Created at: March 27, 2026, 3:03 p.m.