Triple

T18629024
Position Surface form Disambiguated ID Type / Status
Subject Wisconsin School for the Deaf E455360 entity
Predicate city P40 FINISHED
Object Delavan 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: Delavan | Statement: [Wisconsin School for the Deaf, city, Delavan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Delavan
Context triple: [Wisconsin School for the Deaf, city, Delavan]
  • A. Delavan, Wisconsin chosen
    Delavan, Wisconsin is a small city in southeastern Wisconsin known for its historic downtown, lakeside recreation, and role as a regional commercial center.
  • B. River Falls
    River Falls is a small town located in Covington County, Alabama, known for its rural character and proximity to the Conecuh River.
  • C. Janesville
    Janesville is a city in southern Wisconsin known as an industrial and commercial hub along the Rock River.
  • D. Janesville
    Janesville is a small unincorporated community in northeastern California known for its rural character and proximity to the Sierra Nevada and Lassen National Forest.
  • E. Muskego
    Muskego is a suburban city in Waukesha County, Wisconsin, known for its residential communities and numerous lakes and parks.
  • 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_69d8d38cc7948190a55ea64e5638994e completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e54f06f4a081909b64f33814577488 completed April 19, 2026, 9:54 p.m.
Created at: April 10, 2026, 11:46 a.m.