Triple

T15491623
Position Surface form Disambiguated ID Type / Status
Subject Terry Wogan E378699 entity
Predicate employer P7 FINISHED
Object RTÉ E331128 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: RTÉ | Statement: [Terry Wogan, employer, RTÉ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: RTÉ
Context triple: [Terry Wogan, employer, RTÉ]
  • A. RTÉ chosen
    RTÉ is Ireland’s national public service broadcaster, providing television, radio, and online media services.
  • B. RTÉ 2fm
    RTÉ 2fm is a national Irish radio station aimed primarily at a young adult audience, featuring contemporary music, entertainment, and talk programming.
  • C. Broadcasting Authority of Ireland
    The Broadcasting Authority of Ireland is the national body responsible for regulating and overseeing television and radio broadcasting services in Ireland.
  • D. Oireachtas TV
    Oireachtas TV is an Irish public service television channel that broadcasts live and recorded coverage of the proceedings of Ireland’s national parliament, the Oireachtas.
  • E. TG4
    TG4 is an Irish-language public service television channel broadcasting a mix of news, sport, entertainment, and cultural programming in Ireland.
  • 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_69d85cd53a7c819080f5b9042c4c199e completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e03fac2af88190ac1d119e6b21dbe0 completed April 16, 2026, 1:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff365f27c48190822254b6da504d3d completed May 9, 2026, 1:27 p.m.
Created at: April 10, 2026, 3:48 a.m.