Triple

T20398112
Position Surface form Disambiguated ID Type / Status
Subject Science Fiction Theatre E500260 entity
Predicate narratedBy P2181 FINISHED
Object Truman Bradley 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: Truman Bradley | Statement: [Science Fiction Theatre, narratedBy, Truman Bradley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Truman Bradley
Context triple: [Science Fiction Theatre, narratedBy, Truman Bradley]
  • A. Truman Bradley chosen
    Truman Bradley was an American actor and television host best known for narrating and presenting the 1950s anthology series "Science Fiction Theatre."
  • B. Ralph Truman
    Ralph Truman was a British character actor known for his authoritative voice and frequent roles in mid-20th-century historical and adventure films.
  • C. Will Truman
    Will Truman is a witty, neurotic gay lawyer and one of the central protagonists of the sitcom "Will & Grace," known for his close friendship with Grace Adler.
  • D. Spencer Truman
    Spencer Truman is a fictional character from the soap opera "One Life to Live," known as a manipulative and villainous doctor involved in major storylines and complex relationships.
  • E. Donald Dewey
    Donald Dewey is a classification listing used in British hillwalking to categorize certain summits, such as Windy Gyle, based on their height and prominence.
  • 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_69e0b4a81bec8190b69adfdc1336a015 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6798c2b28819092fab93f01218cde completed April 20, 2026, 7:07 p.m.
Created at: April 16, 2026, 11:29 a.m.