Triple

T18838278
Position Surface form Disambiguated ID Type / Status
Subject M-52 E460721 entity
Predicate passesThrough P225 FINISHED
Object Chelsea, 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: Chelsea, Michigan | Statement: [M-52, passesThrough, Chelsea, Michigan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Chelsea, Michigan
Context triple: [M-52, passesThrough, Chelsea, Michigan]
  • A. Chelsea, Michigan chosen
    Chelsea, Michigan is a small city in southeastern Michigan known for its historic downtown, arts and cultural scene, and proximity to Ann Arbor.
  • B. Charlotte, Michigan
    Charlotte, Michigan is a small city in south-central Michigan known as the governmental and commercial hub of Eaton County.
  • C. Atlanta, Michigan
    Atlanta, Michigan is a small unincorporated community in northern Michigan known for its outdoor recreation and role as the administrative center of Montmorency County.
  • D. St. Charles, Michigan
    St. Charles, Michigan is a small village in Saginaw County known for its historic downtown and recreational access to the Shiawassee River.
  • E. Birmingham, Michigan
    Birmingham, Michigan is an affluent suburban city in the Detroit metropolitan area known for its upscale shopping district, walkable downtown, and high quality of life.
  • 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_69d8dcfa11e4819090ab1ef5bdcd2b2e completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5a99f443881909516a82208fd0178 completed April 20, 2026, 4:20 a.m.
Created at: April 10, 2026, 11:56 a.m.