Triple

T11312985
Position Surface form Disambiguated ID Type / Status
Subject Susan Lacy E267887 entity
Predicate partOf P40 FINISHED
Object PBS programming E8587 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: PBS programming | Statement: [Susan Lacy, partOf, PBS programming]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PBS programming
Context triple: [Susan Lacy, partOf, PBS programming]
  • A. PBS chosen
    PBS is a U.S. public television network known for educational, scientific, and cultural programming.
  • B. PBS
    PBS is a U.S. federal agency component responsible for managing and providing government office space and real property for civilian agencies.
  • C. PBS Kids Sprout
    PBS Kids Sprout was a U.S. cable television network focused on preschool children's programming, later rebranded as Universal Kids.
  • D. NBC original programming
    NBC original programming refers to television series and specials that are produced or commissioned by the NBC network for initial broadcast on its channels.
  • E. CNN programming lineup
    CNN programming lineup is the collection of news and current-affairs shows that make up the cable network’s regularly scheduled broadcast schedule.
  • 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_69d6aaca5c24819083db46a30d86cb34 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e9c1b7dc81908d8cc768c47390d3 completed April 9, 2026, 6:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69e50a910a2c8190b8afd4c988e64141 completed April 19, 2026, 5:02 p.m.
Created at: April 8, 2026, 9:32 p.m.