Triple

T22299857
Position Surface form Disambiguated ID Type / Status
Subject Tony Martin E551225 entity
Predicate stageName P7872 FINISHED
Object Tony Martin 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: Tony Martin | Statement: [Tony Martin, stageName, Tony Martin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tony Martin
Context triple: [Tony Martin, stageName, Tony Martin]
  • A. Tony Martin chosen
    Tony Martin is a common name shared by several notable individuals, including a German professional cyclist, an American comedian and actor, and an Australian comedian and writer.
  • B. Tony Martin
    Tony Martin is an English heavy metal vocalist best known for his multiple tenures as lead singer of Black Sabbath during the late 1980s and 1990s.
  • C. Tony Martin
    Tony Martin was an American pop singer and actor popular from the 1930s through the 1950s, known for his smooth baritone voice and appearances in numerous Hollywood musicals.
  • D. Ian Martin
    Ian Martin is a British comedy writer and satirist known for his work on political satires such as the film "The Death of Stalin" and the TV series "The Thick of It."
  • E. Guy Martin
    Guy Martin is a British motorcycle road racer and television presenter known for his Isle of Man TT exploits and engineering-focused TV documentaries.
  • 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_69e11e46c0188190800181a4233f28fe completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1572399148190853c4e91fcf9f38c completed April 29, 2026, 12:56 a.m.
Created at: April 16, 2026, 8:41 p.m.