Triple

T16380419
Position Surface form Disambiguated ID Type / Status
Subject Southfield, Michigan E397790 entity
Predicate borders P224 FINISHED
Object Oak Park, 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: Oak Park, Michigan | Statement: [Southfield, Michigan, borders, Oak Park, Michigan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oak Park, Michigan
Context triple: [Southfield, Michigan, borders, Oak Park, Michigan]
  • A. Oak Park, Michigan chosen
    Oak Park, Michigan is a suburban city in the Detroit metropolitan area known for its residential neighborhoods and diverse community.
  • B. Grosse Pointe Park
    Grosse Pointe Park is a suburban city bordering Detroit in southeastern Michigan, known for its affluent residential character and location along Lake St. Clair.
  • C. Lincoln Park, Michigan
    Lincoln Park, Michigan is a downriver suburban city in Wayne County, just south of Detroit, known for its residential neighborhoods and industrial roots.
  • D. Grosse Pointe, Michigan
    Grosse Pointe, Michigan is an affluent suburban city bordering Detroit, known for its historic lakeside homes, tree-lined streets, and upscale residential character.
  • E. Oak Park
    Oak Park is a public recreational park located in the suburban community of Wyoming, Ohio.
  • 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_69d87f2880b48190ae1a9673a3bbef80 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e319db5b648190a8fca23518a1fb39 completed April 18, 2026, 5:42 a.m.
Created at: April 10, 2026, 5:08 a.m.