Triple

T8582689
Position Surface form Disambiguated ID Type / Status
Subject Hazel Park, Michigan E203221 entity
Predicate borderedBy P224 FINISHED
Object Ferndale, Michigan E211238 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: Ferndale, Michigan | Statement: [Hazel Park, Michigan, borderedBy, Ferndale, Michigan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ferndale, Michigan
Context triple: [Hazel Park, Michigan, borderedBy, Ferndale, Michigan]
  • A. Ferndale, Michigan chosen
    Ferndale, Michigan is a small inner-ring Detroit suburb known for its vibrant downtown, progressive community, and active arts and LGBTQ+ scenes.
  • B. Ferndale
    Ferndale is a former coal-mining town and community located in the Rhondda Fach valley in south Wales.
  • C. Ferndale
    Ferndale is a small city in northwestern Washington State, known for its proximity to the Canadian border and the city of Bellingham.
  • D. Bellevue, Michigan
    Bellevue, Michigan is a small rural village in south-central Michigan known for its historic charm and tight-knit community.
  • E. Watervliet, Michigan
    Watervliet, Michigan is a small city in Berrien County in southwestern Michigan, known for its rural character and proximity to inland lakes and Lake Michigan.
  • 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_69ca8329bb7c8190a63c643730839103 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbeb1d0edc8190b4495935275252f3 completed March 31, 2026, 3:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf9ffe17e481908516d2f526d60684 completed April 3, 2026, 11:09 a.m.
Created at: March 30, 2026, 6:22 p.m.