Triple

T19003095
Position Surface form Disambiguated ID Type / Status
Subject 2023 Cricket World Cup E465004 entity
Predicate mostWicketsPlayer P23687 FINISHED
Object Mohammed Shami 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: Mohammed Shami | Statement: [2023 Cricket World Cup, mostWicketsPlayer, Mohammed Shami]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mohammed Shami
Context triple: [2023 Cricket World Cup, mostWicketsPlayer, Mohammed Shami]
  • A. Mohammad Shami chosen
    Mohammad Shami is an Indian international fast bowler renowned for his ability to swing the ball at high pace and for being one of India's leading wicket-takers across formats.
  • B. Shardul Thakur
    Shardul Thakur is an Indian international fast-bowling all-rounder known for his wicket-taking ability and crucial lower-order runs across formats.
  • C. Jasprit Bumrah
    Jasprit Bumrah is an Indian fast bowler renowned for his unorthodox action, pinpoint yorkers, and status as one of the world’s leading limited-overs and Test pacers.
  • D. Bhuvneshwar Kumar
    Bhuvneshwar Kumar is an Indian international cricketer renowned for his swing bowling and death-overs expertise, particularly in limited-overs formats.
  • E. Jadeja
    The Jadeja are a Rajput clan historically prominent as rulers and landholders in parts of Gujarat and surrounding regions in western India.
  • 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_69d8dd01a56c81909694a128c66b21d7 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d6a252588190a40398b1879fb096 completed April 20, 2026, 7:32 a.m.
Created at: April 10, 2026, 12:01 p.m.