Triple

T16804500
Position Surface form Disambiguated ID Type / Status
Subject Manitou Passage E408442 entity
Predicate near P350 FINISHED
Object Empire, Michigan E277969 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: Empire, Michigan | Statement: [Manitou Passage, near, Empire, Michigan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Empire, Michigan
Context triple: [Manitou Passage, near, Empire, Michigan]
  • A. Empire, Michigan chosen
    Empire, Michigan is a small village on the shores of Lake Michigan known as a gateway to the Sleeping Bear Dunes National Lakeshore.
  • B. Pierson, Michigan
    Pierson, Michigan is a small village located in Montcalm County in the western part of the U.S. state of Michigan.
  • C. Albion, Michigan
    Albion, Michigan is a small city in south-central Michigan known historically as an industrial and railroad hub and as the home of Albion College.
  • D. Armada, Michigan
    Armada, Michigan is a small rural village in Macomb County known for its tight-knit community and annual Armada Fair.
  • E. Dorr, Michigan
    Dorr, Michigan is a small unincorporated community in Allegan County known for its rural character and role as a local residential and commercial center within Dorr Township.
  • 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_69d88393905081908d00a86b99996ac8 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b2cb68508190a05749bad68f7b43 completed April 18, 2026, 4:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a015fb6aff481908cb3d03b229ebf11 completed May 11, 2026, 4:48 a.m.
Created at: April 10, 2026, 5:22 a.m.