Triple

T17418773
Position Surface form Disambiguated ID Type / Status
Subject BT Sport 1 E423553 entity
Predicate hasSisterChannel P6991 FINISHED
Object BT Sport 3 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: BT Sport 3 | Statement: [BT Sport 1, hasSisterChannel, BT Sport 3]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BT Sport 3
Context triple: [BT Sport 1, hasSisterChannel, BT Sport 3]
  • A. BT Sport 3 chosen
    BT Sport 3 is a British pay television sports channel that broadcasts a range of live and recorded sporting events, including European football, combat sports, and other international competitions.
  • B. BT Sport 2
    BT Sport 2 is a British pay television sports channel offering live coverage of a wide range of domestic and international sporting events.
  • C. BT Sport 1
    BT Sport 1 is a British sports television channel operated by BT that broadcasts live coverage of major football, rugby, and other sporting events.
  • D. BT Sport Ultimate
    BT Sport Ultimate is BT Sport’s premium ultra-high-definition sports channel offering enhanced picture quality and immersive viewing for major live sporting events.
  • E. BT Sport
    BT Sport is a group of British sports television channels that broadcast a wide range of live sporting events, including top-tier football, rugby, and other major competitions.
  • 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_69d889d7d27c819088486ce3f0627fa1 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e44234d840819096484a15d407785a completed April 19, 2026, 2:47 a.m.
Created at: April 10, 2026, 5:46 a.m.