Triple

T22356288
Position Surface form Disambiguated ID Type / Status
Subject Ravi Shastri E552659 entity
Predicate workedFor P1910 FINISHED
Object Star Sports 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: Star Sports | Statement: [Ravi Shastri, workedFor, Star Sports]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Star Sports
Context triple: [Ravi Shastri, workedFor, Star Sports]
  • A. Star Sports chosen
    Star Sports is a major group of sports television channels in India known for broadcasting cricket and other popular sporting events across the Indian subcontinent.
  • B. Premier Sports
    Premier Sports is a UK-based subscription sports television channel known for broadcasting a range of live sporting events, including football competitions.
  • C. Eurosport
    Eurosport is a pan-European sports television network and streaming platform known for broadcasting a wide range of international sporting events, including major tournaments and Olympic Games.
  • D. Sky Sport
    Sky Sport is an Italian group of pay-TV sports channels operated by Sky Italia, known for broadcasting major national and international sporting events.
  • E. Sony Sports Network
    Sony Sports Network is an Indian sports television network that broadcasts a wide range of domestic and international sporting events, including cricket, football, and combat sports.
  • 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_69e11e4a0ad08190a385b4d343cf6524 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f157cf94508190b0f2c63ddfecb813 completed April 29, 2026, 12:58 a.m.
Created at: April 16, 2026, 8:44 p.m.