Triple

T12989763
Position Surface form Disambiguated ID Type / Status
Subject Kanu E321871 entity
Predicate memberOfSportsTeam P330 FINISHED
Object Ajax E386269 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: Ajax | Statement: [Kanu, memberOfSportsTeam, Ajax]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ajax
Context triple: [Kanu, memberOfSportsTeam, Ajax]
  • A. Ajax
    Ajax is a long-standing household cleaning product brand known for its powdered and liquid cleaners, owned by Colgate-Palmolive.
  • B. Ajax
    Ajax is an ancient Greek tragedy by Sophocles that dramatizes the downfall and suicide of the great warrior Ajax after the Trojan War.
  • C. Ajax chosen
    Ajax is a renowned Dutch football club from Amsterdam, famous for its successful history, attacking style of play, and prolific youth academy.
  • D. Ajax
    Ajax is a modern British Army armoured fighting vehicle designed for advanced reconnaissance, surveillance, and battlefield intelligence roles.
  • E. Ajax
    Ajax is a sadistic mutant villain from Marvel's Deadpool comics and film, known for torturing Wade Wilson and inadvertently creating Deadpool.
  • 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_69d8076479b8819090afce3591939cdf completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97e75b9f88190a54372c2a1223a4e completed April 10, 2026, 10:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6b8f942588190b69a3067d5145182 completed May 3, 2026, 2:54 a.m.
Created at: April 9, 2026, 8:43 p.m.