Triple

T18000140
Position Surface form Disambiguated ID Type / Status
Subject Olivet College E430606 entity
Predicate locatedIn P40 FINISHED
Object Olivet, 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: Olivet, Michigan | Statement: [Olivet College, locatedIn, Olivet, Michigan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Olivet, Michigan
Context triple: [Olivet College, locatedIn, Olivet, Michigan]
  • A. Olivet, Michigan chosen
    Olivet, Michigan is a small city in south-central Michigan best known as the home of Olivet College.
  • B. Athens, Michigan
    Athens, Michigan is a small village in southern Michigan known for its rural character and location within the Battle Creek metropolitan area.
  • C. Hillsdale, Michigan
    Hillsdale, Michigan is a small city and county seat known for its historic downtown and as the home of Hillsdale College.
  • D. Beverly Hills, Michigan
    Beverly Hills, Michigan is a small, affluent suburban village in Oakland County known for its residential character and proximity to Detroit.
  • E. Clio, Michigan
    Clio, Michigan is a small city in Genesee County known as a suburban community near Flint with a mix of residential neighborhoods and local businesses.
  • 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_69d8b90364248190a37381adea932f42 completed April 10, 2026, 8:46 a.m.
NER Named-entity recognition batch_69e4b3e75e908190a6ff6a3ec6069ff5 completed April 19, 2026, 10:52 a.m.
Created at: April 10, 2026, 10:23 a.m.