Triple

T1069704
Position Surface form Disambiguated ID Type / Status
Subject Ecorse, Michigan E23296 entity
Predicate adjacentTo P224 FINISHED
Object Wyandotte, Michigan E229832 NE FINISHED

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: Wyandotte, Michigan | Statement: [Ecorse, Michigan, adjacentTo, Wyandotte, Michigan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wyandotte, Michigan
Context triple: [Ecorse, Michigan, adjacentTo, Wyandotte, Michigan]
  • A. Wyandotte, Michigan chosen
    Wyandotte, Michigan is a small industrial city and Downriver suburb of Detroit located along the western shore of the Detroit River.
  • B. Westland, Michigan
    Westland, Michigan is a suburban city in Wayne County within the Detroit metropolitan area, known primarily as a residential and retail community.
  • C. Wayne, Michigan
    Wayne, Michigan is a small city in southeastern Michigan that forms part of the Detroit metropolitan area and has a history tied to the region’s automotive and industrial development.
  • D. Hudsonville, Michigan
    Hudsonville, Michigan is a small suburban city in western Michigan known for its family-friendly community and proximity to Grand Rapids.
  • E. Midland, Michigan
    Midland, Michigan is a small city in central Michigan known as a hub for the chemical industry and the longtime headquarters of Dow Chemical Company.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a493ee1f908190992b5f0d1b04459b completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b914b4908190886d6698294c6b5b completed March 1, 2026, 10:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69ae95c9bbfc81909a02cdca9c859d01 completed March 9, 2026, 9:41 a.m.
Created at: March 1, 2026, 7:42 p.m.