Triple

T2704138
Position Surface form Disambiguated ID Type / Status
Subject American Experience E59302 entity
Predicate productionCompany P490 FINISHED
Object WGBH E178162 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: WGBH | Statement: [American Experience, productionCompany, WGBH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: WGBH
Context triple: [American Experience, productionCompany, WGBH]
  • A. WGBH Boston chosen
    WGBH Boston is a major American public television and radio broadcaster known for producing influential educational and science programs for PBS.
  • B. WCVB-TV
    WCVB-TV is a Boston-based television station serving as the ABC network affiliate for the Greater Boston area.
  • C. Corporation for Public Broadcasting
    The Corporation for Public Broadcasting is a nonprofit corporation created by the U.S. government to fund and support public television and radio, including networks like PBS and NPR.
  • D. WNET
    WNET is a major New York City public television station and one of the primary flagship producers of national programming for PBS.
  • E. PBS
    PBS is a U.S. public television network known for educational, scientific, and cultural programming.
  • 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_69ab4ac66bc88190b9e4afa5fc843f72 completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abda518c58819096c8b67c0f754655 completed March 7, 2026, 7:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69afc63b76e0819084c4d2bd4a9e6d78 completed March 10, 2026, 7:20 a.m.
Created at: March 6, 2026, 9:55 p.m.