Triple

T15868225
Position Surface form Disambiguated ID Type / Status
Subject BBC mobile applications E384765 entity
Predicate includes P1393 FINISHED
Object BBC Sounds app E77611 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: BBC Sounds app | Statement: [BBC mobile applications, includes, BBC Sounds app]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BBC Sounds app
Context triple: [BBC mobile applications, includes, BBC Sounds app]
  • A. BBC Sounds chosen
    BBC Sounds is the BBC’s digital audio platform offering live radio, music mixes, and podcasts across web and mobile apps.
  • B. CBC Listen app
    The CBC Listen app is a digital streaming platform from the Canadian Broadcasting Corporation that lets users access live CBC Radio, music streams, and on-demand podcasts.
  • C. BBC Audio
    BBC Audio is a division of the BBC responsible for producing and managing the corporation’s radio, podcast, and other audio content services.
  • D. BBC News app
    The BBC News app is a mobile application that provides users with up-to-date news coverage, live reporting, and analysis from the BBC’s global network of journalists.
  • E. BBC Digital Radio
    BBC Digital Radio is the BBC’s suite of digital-only radio services, offering a range of specialized and archive-based stations beyond its traditional analogue networks.
  • 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_69d86da4e86481909f1325fdc971b5ec completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1556118a08190a13dc2db3d796b11 completed April 16, 2026, 9:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffa947ba3881909c602f2fc60dd6e8 completed May 9, 2026, 9:38 p.m.
Created at: April 10, 2026, 4:50 a.m.