Triple

T21766836
Position Surface form Disambiguated ID Type / Status
Subject Dragon Seed E537315 entity
Predicate editor P1954 FINISHED
Object Frank Sullivan 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: Frank Sullivan | Statement: [Dragon Seed, editor, Frank Sullivan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Sullivan
Context triple: [Dragon Seed, editor, Frank Sullivan]
  • A. Frank Sullivan
    Frank Sullivan is an American college basketball coach best known for his long tenure leading the Harvard Crimson men's basketball program.
  • B. Frank Sullivan chosen
    Frank Sullivan was a film editor known for his work on classic Hollywood productions, including the musical "Babes in Arms."
  • C. Frank Sullivan
    Frank Sullivan is the fictional New York City firefighter and father who communicates across time with his son via a ham radio in the science fiction film "Frequency."
  • D. Frank Sullivan
    Frank Sullivan was an American Major League Baseball right-handed pitcher, best known for his All-Star seasons with the Boston Red Sox in the 1950s.
  • E. Fred Sullivan
    Fred Sullivan was the elder brother of composer Arthur Sullivan and a British actor and singer associated with Victorian theatre.
  • 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_69e0c46f5d1c8190bf830409e98464e5 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f031aa9c888190887c5c1d1e3bab9f completed April 28, 2026, 4:03 a.m.
Created at: April 16, 2026, 6:51 p.m.