Triple

T14645994
Position Surface form Disambiguated ID Type / Status
Subject Edgar Bergen E343849 entity
Predicate employer P7 FINISHED
Object CBS Radio E34492 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: CBS Radio | Statement: [Edgar Bergen, employer, CBS Radio]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CBS Radio
Context triple: [Edgar Bergen, employer, CBS Radio]
  • A. CBS Radio chosen
    CBS Radio was a major American radio network that became widely known for broadcasting President Franklin D. Roosevelt’s influential Fireside Chats and other national news and entertainment programs during the 20th century.
  • B. NBC Radio
    NBC Radio was a major American radio network that broadcast national news, entertainment, and sports programming throughout much of the 20th century.
  • C. CBS News Radio
    CBS News Radio is a U.S. radio network that provides national and international news, features, and special reports to affiliated radio stations.
  • D. WBZ-FM
    WBZ-FM is a Boston-area sports radio station known for its all-sports format and coverage of local professional teams.
  • E. Rogers Broadcasting
    Rogers Broadcasting was the former name of the Canadian media company now known as Rogers Media, which operates television, radio, and digital media properties across Canada.
  • 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_69d822e1a2cc81908e5bb93cf61ce3cc completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb4ea6d8481908e6331ca173c646b completed April 14, 2026, 9:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69fde170d4a0819087caeacf39f95954 completed May 8, 2026, 1:13 p.m.
Created at: April 10, 2026, 1:26 a.m.