Triple

T19937009
Position Surface form Disambiguated ID Type / Status
Subject CNN International E479198 entity
Predicate formerName P65 FINISHED
Object CNN International Network NE NERFINISHED

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: CNN International Network | Statement: [CNN International, formerName, CNN International Network]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CNN International Network
Context triple: [CNN International, formerName, CNN International Network]
  • A. CNN International chosen
    CNN International is a global 24-hour news television channel providing international news coverage and analysis to audiences worldwide.
  • B. CNN.com
    CNN.com is the online news website of CNN, providing global news coverage, analysis, and multimedia content.
  • C. CNN2
    CNN2 was the original name of HLN, a U.S. cable news channel that focused on headline news and brief, continuously updated reports.
  • D. CBS Broadcast International
    CBS Broadcast International was the global television distribution and syndication arm of the CBS network, responsible for licensing and marketing CBS programming to international broadcasters.
  • E. CNN
    CNN is a major American cable news television channel known for pioneering 24-hour news coverage and live reporting from global events.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e522a17c819095165d4d24939fd8 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65a17fb2c8190b3aaae88e741648a completed April 20, 2026, 4:53 p.m.
Created at: April 10, 2026, 1:53 p.m.