Triple

T17389489
Position Surface form Disambiguated ID Type / Status
Subject Escanaba River E422778 entity
Predicate mouthLocatedNear P18935 FINISHED
Object Escanaba, 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: Escanaba, Michigan | Statement: [Escanaba River, mouthLocatedNear, Escanaba, Michigan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Escanaba, Michigan
Context triple: [Escanaba River, mouthLocatedNear, Escanaba, Michigan]
  • A. Escanaba, Michigan chosen
    Escanaba, Michigan is a small port city on Little Bay de Noc in Michigan’s Upper Peninsula, known for its shipping, paper industry, and outdoor recreation.
  • B. Skandia, Michigan
    Skandia, Michigan is a small rural community located in Michigan’s Upper Peninsula, known for its forested landscapes and proximity to Lake Superior.
  • C. Osseo, Michigan
    Osseo, Michigan is a small rural village located in Hillsdale County in the southern part of the state.
  • D. Fairport, Michigan
    Fairport, Michigan is a small unincorporated lakeside community located at the southern tip of Michigan’s Garden Peninsula on Lake Michigan.
  • E. Negaunee, Michigan
    Negaunee, Michigan is a small city in Michigan's Upper Peninsula known for its iron mining history and location near Marquette.
  • 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_69d889d710288190bf0f4762801fefae completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a8c718c81909cb20749aaf12897 completed April 19, 2026, 2:14 a.m.
Created at: April 10, 2026, 5:45 a.m.