Triple

T20701196
Position Surface form Disambiguated ID Type / Status
Subject Tomorrowland E508785 entity
Predicate castMember P1668 FINISHED
Object Thomas Robinson 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: Thomas Robinson | Statement: [Tomorrowland, castMember, Thomas Robinson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas Robinson
Context triple: [Tomorrowland, castMember, Thomas Robinson]
  • A. Thomas Robinson
    Thomas Robinson was the son of Irish astronomer and physicist John Thomas Romney Robinson.
  • B. Thomas Robinson chosen
    Thomas Robinson is an American child actor best known for his role in the comedy film "The Switch."
  • C. Charles Alverson
    Charles Alverson was an American writer and editor best known for his work in speculative fiction and his collaborations with Terry Gilliam on film projects.
  • D. Richard Sampson
    Richard Sampson was a 16th-century English clergyman, canon lawyer, and bishop who played a notable role in the ecclesiastical politics of Henry VIII’s reign.
  • E. Christian Anthony Mathis
    Christian Anthony Mathis, better known by his stage name Trick Trick, is an American rapper, producer, and hip-hop figure from Detroit known for his work in the city's underground and mainstream rap scenes.
  • 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_69e0b4c2b2a481909e31e9cb8f81ab55 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6c18bfac08190bf80beeb3ce1951a completed April 21, 2026, 12:15 a.m.
Created at: April 16, 2026, 12:12 p.m.