Triple

T22657130
Position Surface form Disambiguated ID Type / Status
Subject Ajax Cape Town F.C. E559256 entity
Predicate wonCompetition P2624 FINISHED
Object ABSA Cup 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: ABSA Cup | Statement: [Ajax Cape Town F.C., wonCompetition, ABSA Cup]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ABSA Cup
Context triple: [Ajax Cape Town F.C., wonCompetition, ABSA Cup]
  • A. ABSA Cup chosen
    The ABSA Cup was a South African knockout football competition that served as a predecessor to the Nedbank Cup in the country’s domestic soccer calendar.
  • B. Jordan Cup
    The Jordan Cup is the premier national knockout football (soccer) cup competition organized by the Jordan Football Association.
  • C. ADIB Cup
    The ADIB Cup is a professional football league cup competition in the United Arab Emirates featuring clubs from the country's top divisions.
  • D. Aiteo Cup
    The Aiteo Cup is Nigeria’s premier national football knockout competition, featuring clubs from across the country in both men’s and women’s categories.
  • E. Pinatar Cup
    The Pinatar Cup is an invitational international women's football tournament held annually in Spain, featuring national teams competing in friendly matches as part of their preparation and development.
  • 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_69e245489dd88190b1f674acf61c8769 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1765c62bc8190b3fcde76d6b6dfb6 completed April 29, 2026, 3:09 a.m.
Created at: April 17, 2026, 3:06 p.m.