Triple

T23252971
Position Surface form Disambiguated ID Type / Status
Subject Sparta, Wisconsin E581783 entity
Predicate hasNearbyCity P350 FINISHED
Object Tomah, Wisconsin 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: Tomah, Wisconsin | Statement: [Sparta, Wisconsin, hasNearbyCity, Tomah, Wisconsin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tomah, Wisconsin
Context triple: [Sparta, Wisconsin, hasNearbyCity, Tomah, Wisconsin]
  • A. Tomah, Wisconsin chosen
    Tomah, Wisconsin is a small city in Monroe County known as a regional transportation hub and gateway to nearby military and outdoor recreation areas in west-central Wisconsin.
  • B. Tomahawk, Wisconsin
    Tomahawk, Wisconsin is a small city in northern Wisconsin known for its outdoor recreation, lakes, and annual fall motorcycle rally.
  • C. Mattoon, Wisconsin
    Mattoon, Wisconsin is a small rural village located in Langlade County in the north-central region of the state.
  • D. Tacoma, Wisconsin
    Tacoma, Wisconsin is a small unincorporated community located within Fond du Lac County in the U.S. state of Wisconsin.
  • E. Watertown, Wisconsin
    Watertown, Wisconsin is a small city in southeastern Wisconsin known for its historic downtown, riverside setting, and early German-American heritage.
  • 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_69e24606b17c81908aba1a4911c8a8ba completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f193f840dc819098e52272abefe616 completed April 29, 2026, 5:15 a.m.
Created at: April 17, 2026, 4:11 p.m.