Triple

T23093677
Position Surface form Disambiguated ID Type / Status
Subject Williams family E575825 entity
Predicate associatedWith P37 FINISHED
Object Proctor family 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: Proctor family | Statement: [Williams family, associatedWith, Proctor family]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Proctor family
Context triple: [Williams family, associatedWith, Proctor family]
  • A. Proctor family chosen
    The Proctor family is a prominent Utica, New York family known for its philanthropy and patronage of the arts, including major support for the Munson-Williams-Proctor Arts Institute.
  • B. Parris family
    The Parris family is a historical New England family best known for its association with the Salem witch trials through its member Reverend Samuel Parris and his household.
  • C. Proctor
    Proctor is a small town in Rutland County, Vermont, historically known for its marble industry and close-knit community.
  • D. Proctor
    Proctor is a surname most notably associated with Samuel DeWitt Proctor, an influential American minister, educator, and civil rights leader.
  • E. Proctor
    Proctor is a character in J.G. Ballard’s novel "Concrete Island," playing a key role in the psychological and social dynamics that unfold on the isolated traffic island.
  • 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_69e245c060b48190a9bd61a47a16db17 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18de2ed088190971ff08c58b15aad completed April 29, 2026, 4:49 a.m.
Created at: April 17, 2026, 3:57 p.m.