Triple

T6974568
Position Surface form Disambiguated ID Type / Status
Subject South African Premier Division E161683 entity
Predicate sponsor P67 FINISHED
Object DStv E633650 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: DStv | Statement: [South African Premier Division, sponsor, DStv]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: DStv
Context triple: [South African Premier Division, sponsor, DStv]
  • A. DStv chosen
    DStv is a major Sub-Saharan African satellite television service owned by MultiChoice, known for offering extensive sports and entertainment broadcasting across the region.
  • B. Foxtel
    Foxtel is a major Australian pay television and streaming company offering a wide range of entertainment, sports, and news content.
  • C. Sling TV
    Sling TV is an American over-the-top internet television service that offers live and on-demand streaming of cable channels without a traditional cable subscription.
  • D. NOW TV
    NOW TV is a subscription-based streaming television service offering on-demand movies, entertainment, and sports content, primarily in the UK and Ireland.
  • E. Star TV
    Star TV is a major Asian satellite television network known for its broad entertainment and news programming across multiple countries.
  • 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_69c68854a0d88190bc0bf82263f1afce completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6db3bda908190a10a91dc8d043ef1 completed March 27, 2026, 7:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69c76a0735548190a406387c929cca07 completed March 28, 2026, 5:41 a.m.
Created at: March 27, 2026, 2:30 p.m.