Triple

T18112862
Position Surface form Disambiguated ID Type / Status
Subject The Flamingos E433523 entity
Predicate member P10 FINISHED
Object Tommy Hunt 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: Tommy Hunt | Statement: [The Flamingos, member, Tommy Hunt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tommy Hunt
Context triple: [The Flamingos, member, Tommy Hunt]
  • A. Tommy Hunt chosen
    Tommy Hunt is an American soul singer best known as a former member of The Flamingos and for his solo work on Scepter Records in the 1960s.
  • B. Michael Gregson
    Michael Gregson is a fictional London magazine editor and suitor of Lady Edith Crawley in the British period drama series "Downton Abbey."
  • C. Tommy Ballantine
    Tommy Ballantine is a fictional character from the television series "Kristin."
  • D. Rob Waddell
    Rob Waddell is a New Zealand rower best known for winning Olympic gold in the single sculls at the 2000 Sydney Games and later competing in elite sailing, including the America’s Cup.
  • E. Eddie Plank
    Eddie Plank was a Hall of Fame left-handed pitcher for the Philadelphia Athletics in the early 20th century, renowned for his exceptional control and longevity on the mound.
  • 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_69d8b90916008190a1f110bd7ced5473 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4ddd3fd9c81909bfe95927f7553e3 completed April 19, 2026, 1:51 p.m.
Created at: April 10, 2026, 10:28 a.m.