Triple

T17002202
Position Surface form Disambiguated ID Type / Status
Subject Mel Allen E412474 entity
Predicate employer P7 FINISHED
Object NBC E2196 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: NBC | Statement: [Mel Allen, employer, NBC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: NBC
Context triple: [Mel Allen, employer, NBC]
  • A. NBC chosen
    NBC is a major American broadcast television network known for its nationwide programming, including news, sports, and entertainment.
  • B. NBC
    NBC is a major westward-flowing ocean current along the northern coast of Brazil that transports warm water from the equatorial Atlantic toward the Caribbean.
  • C. NBC USA
    NBC USA is a major African American Christian denomination in the United States, formally known as the National Baptist Convention, USA, Inc.
  • D. CBS
    CBS is a college within the University of California, Davis that focuses on education and research in the biological sciences.
  • E. CBS
    CBS is the commonly used abbreviation for the Commission for Basic Systems, a specialized body focused on foundational infrastructure and standards, likely within an international or governmental organizational context.
  • 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_69d886cb581c8190ab05f4b429c9cd85 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d37ec2b48190b4f997899d887ba8 completed April 18, 2026, 6:54 p.m.
NED1 Entity disambiguation (via context triple) batch_6a011b451ff88190b63f4ebddf93f153 completed May 10, 2026, 11:56 p.m.
Created at: April 10, 2026, 5:32 a.m.