Triple

T18363475
Position Surface form Disambiguated ID Type / Status
Subject Stephen Tyng Mather E439978 entity
Predicate familyName P18 FINISHED
Object Mather 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: Mather | Statement: [Stephen Tyng Mather, familyName, Mather]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mather
Context triple: [Stephen Tyng Mather, familyName, Mather]
  • A. Mather chosen
    Mather is a surname most notably associated with the prominent New England Puritan minister and author Cotton Mather and his influential family.
  • B. Mather
    Mather is a community in Sacramento County, California, known for its former Air Force base and its role within the Sacramento metropolitan area.
  • C. Berkely Mather
    Berkely Mather was a British writer and screenwriter known for his crime and adventure novels as well as his work on several mid-20th-century films.
  • D. Arbella
    Arbella was the flagship that carried John Winthrop and other Puritan settlers to New England during the Great Migration of 1630.
  • E. Revere
    Revere is a surname most notably associated with American historical figure Paul Revere and various other individuals in politics, arts, and public life.
  • 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_69d8b918221c8190a9f7b563d64ac677 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e516de778c8190a75335ced4e1f834 completed April 19, 2026, 5:54 p.m.
Created at: April 10, 2026, 10:37 a.m.