Triple

T11715020
Position Surface form Disambiguated ID Type / Status
Subject Michael Schultz E278473 entity
Predicate directed P7373 FINISHED
Object Carbon Copy E942595 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: Carbon Copy | Statement: [Michael Schultz, directed, Carbon Copy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carbon Copy
Context triple: [Michael Schultz, directed, Carbon Copy]
  • A. Carbon Copy chosen
    Carbon Copy is a 1981 American comedy film starring George Segal and Denzel Washington in his feature-film debut.
  • B. Copia
    Copia was a later Roman colony in southern Italy that succeeded the ancient Greek city of Thurii.
  • C. Copycat
    Copycat is a 1995 psychological thriller film about a criminal psychologist and a detective hunting a serial killer who imitates the methods of infamous murderers.
  • D. Hay copy
    The Hay copy is one of the principal handwritten manuscript versions of Abraham Lincoln’s Gettysburg Address, prepared by Lincoln for his private secretary John Hay and notable for its textual variations from other surviving drafts.
  • E. Copywrite
    Copywrite is an American underground hip-hop MC from Columbus, Ohio, known for his sharp battle rhymes and work with the group MHz Legacy.
  • 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_69d6aaff2ce88190b4a1e4b341ad5377 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a4bf54d88190a8e07fbbf8d9e962 completed April 10, 2026, 7:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69f0197d03c08190a5515ffe3cc887ea completed April 28, 2026, 2:20 a.m.
Created at: April 8, 2026, 9:40 p.m.