Triple

T22707647
Position Surface form Disambiguated ID Type / Status
Subject William Sublette E561501 entity
Predicate familyName P18 FINISHED
Object Sublette 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: Sublette | Statement: [William Sublette, familyName, Sublette]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sublette
Context triple: [William Sublette, familyName, Sublette]
  • A. Sublette chosen
    Sublette is a surname most notably associated with William Lewis Sublette, an American fur trader, explorer, and pioneer of the early 19th century American West.
  • B. Culberson County
    Culberson County is a sparsely populated county in far western Texas known for its desert landscapes and the Guadalupe Mountains, including the highest peak in the state.
  • C. Sheridan County
    Sheridan County is a rural county in northwestern Kansas known for its agricultural landscape and small communities such as Selden.
  • D. Beaverhead County
    Beaverhead County is a large, sparsely populated county in southwestern Montana known for its ranching, outdoor recreation, and the presence of Bannack, the state's first territorial capital.
  • E. Fremont County
    Fremont County is a rural county in the southwestern corner of Iowa known for its agricultural landscape and small communities.
  • 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_69e2454f1348819088d83f420925a5c1 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f178cff7588190a40c8cef0f3cd44a completed April 29, 2026, 3:19 a.m.
Created at: April 17, 2026, 3:17 p.m.