Triple

T19009550
Position Surface form Disambiguated ID Type / Status
Subject Glen Williams E465182 entity
Predicate namedAfter P63 FINISHED
Object Williams 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: Williams family | Statement: [Glen Williams, namedAfter, Williams family]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Williams family
Context triple: [Glen Williams, namedAfter, Williams family]
  • A. Williams family chosen
    The Williams family is a prominent American family known for its philanthropy and patronage of the arts, notably supporting institutions such as the Munson-Williams-Proctor Arts Institute.
  • B. Kelly family
    The Kelly family is a prominent Irish-American crime family historically involved in organized criminal activities.
  • C. Ryan family
    The Ryan family is an Irish lineage from which the surname O'Ryan originates, reflecting ancestral descent and heritage.
  • D. Ryan family
    The Ryan family is an American political family best known for including former U.S. House Speaker Paul Ryan and his wife, tax attorney and political figure Janna Little Ryan.
  • E. Tyler family
    The Tyler family is a historically significant family associated with the land and legacy that became the Tyler Arboretum in Pennsylvania.
  • 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_69d8dd025c188190a1d81f5b4ec7e2c6 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d6a72aa88190a04f13cd14ee77d4 completed April 20, 2026, 7:32 a.m.
Created at: April 10, 2026, 12:02 p.m.