Triple

T19695091
Position Surface form Disambiguated ID Type / Status
Subject The Million-Year Picnic E472935 entity
Predicate mainCharacter P1183 FINISHED
Object William Thomas 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: William Thomas | Statement: [The Million-Year Picnic, mainCharacter, William Thomas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Thomas
Context triple: [The Million-Year Picnic, mainCharacter, William Thomas]
  • A. William Thomas
    William Thomas was a prominent 19th-century architect known for his influential work on major public monuments and buildings in Canada.
  • B. William Thomas
    William Thomas was an early settler and prominent figure in the Plymouth Colony town of Marshfield in 17th-century New England.
  • C. William Thomas
    William Thomas was a 16th-century English courtier, scholar, and political writer who served as a key advisor during the reign of Edward VI.
  • D. William Thomas chosen
    William Thomas is an actor known for his role in the British television series "Mine All Mine."
  • E. William Thomas
    William Thomas is an actor best known for his role in the British television series "Twin Town."
  • 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_69d8e515bef88190bc30781aea50537a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6421385e88190b22b12ab3d851dea completed April 20, 2026, 3:11 p.m.
Created at: April 10, 2026, 1:46 p.m.