Triple

T19806218
Position Surface form Disambiguated ID Type / Status
Subject City of Douglas E475817 entity
Predicate county P75 FINISHED
Object Allegan County 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: Allegan County | Statement: [City of Douglas, county, Allegan County]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Allegan County
Context triple: [City of Douglas, county, Allegan County]
  • A. Allegan County chosen
    Allegan County is a county in southwestern Michigan known for its mix of Lake Michigan shoreline, agricultural land, and small towns.
  • B. Huron County
    Huron County is a predominantly rural county in southwestern Ontario, Canada, known for its agriculture, small towns, and Lake Huron shoreline.
  • C. Huron County
    Huron County is a county in northern Ohio known for its mix of small cities, rural communities, and agricultural land.
  • D. Barry County
    Barry County is a rural county in southwestern Michigan known for its lakes, forests, and small communities between the Grand Rapids and Kalamazoo metropolitan areas.
  • E. Waushara County
    Waushara County is a rural county in central Wisconsin known for its lakes, forests, and outdoor recreation.
  • 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_69d8e51bc4208190a1c57d8c5d1b15e4 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65428081c8190b394c442f4c2a9a6 completed April 20, 2026, 4:28 p.m.
Created at: April 10, 2026, 1:49 p.m.