Triple

T17966628
Position Surface form Disambiguated ID Type / Status
Subject Harbor Springs E449224 entity
Predicate hasNearbyCity P350 FINISHED
Object Petoskey 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: Petoskey | Statement: [Harbor Springs, hasNearbyCity, Petoskey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Petoskey
Context triple: [Harbor Springs, hasNearbyCity, Petoskey]
  • A. Petoskey chosen
    Petoskey is a resort and tourist city on the shores of Lake Michigan in northern Michigan, known for its scenic waterfront and distinctive fossilized coral stones called Petoskey stones.
  • B. Houghton
    Houghton is a residential and waterfront neighborhood in the city of Kirkland, Washington, known for its parks, lake access, and small-town feel within the greater Seattle metropolitan area.
  • C. Houghton
    Houghton is an English surname most prominently associated with Steph Houghton, a renowned England women's footballer and former national team captain.
  • D. Houghton
    Houghton is a wealthy, historically significant suburb of Johannesburg, South Africa, known for being the longtime home of Nelson Mandela.
  • E. Houghton
    Houghton is a surname and place name of English origin, commonly found in the United Kingdom and former British colonies.
  • 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_69d8b9f9927c8190a006110c8b996e61 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4b1380960819089a3c0dd7cd57e5e completed April 19, 2026, 10:40 a.m.
Created at: April 10, 2026, 10:22 a.m.