Triple

T12586173
Position Surface form Disambiguated ID Type / Status
Subject M-43 E300467 entity
Predicate passesThrough P225 FINISHED
Object Gobles, Michigan 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: Gobles, Michigan | Statement: [M-43, passesThrough, Gobles, Michigan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gobles, Michigan
Context triple: [M-43, passesThrough, Gobles, Michigan]
  • A. Gobles, Michigan chosen
    Gobles, Michigan is a small city located in southwestern Michigan known for its rural character and proximity to lakes and outdoor recreation.
  • B. Gladstone, Michigan
    Gladstone, Michigan is a small city in Michigan’s Upper Peninsula known for its waterfront location on Little Bay de Noc and its outdoor recreation opportunities.
  • C. Bergland, Michigan
    Bergland, Michigan is a small unincorporated community in Ontonagon County in Michigan’s Upper Peninsula, known for its location near Lake Gogebic and along major regional travel routes.
  • D. Sagamore, Michigan
    Sagamore, Michigan is a small unincorporated community located within Dickinson County in Michigan’s Upper Peninsula.
  • E. Elberta, Michigan
    Elberta, Michigan is a small village on Lake Michigan in Benzie County known historically as a Great Lakes port and rail terminus.
  • 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_69d7bde87b648190bcd0266e9efde098 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d954bbe72c8190aa11090bb6b480c9 completed April 10, 2026, 7:51 p.m.
Created at: April 9, 2026, 5:05 p.m.