Triple

T14027403
Position Surface form Disambiguated ID Type / Status
Subject Kake, Alaska E337496 entity
Predicate borough P300 FINISHED
Object Petersburg Borough E773863 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: Petersburg Borough | Statement: [Kake, Alaska, borough, Petersburg Borough]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Petersburg Borough
Context triple: [Kake, Alaska, borough, Petersburg Borough]
  • A. Petersburg Borough chosen
    Petersburg Borough is a local government area in southeastern Alaska encompassing the fishing community of Petersburg and surrounding islands and waterways.
  • B. Beauport borough
    Beauport borough is a residential and historic district of Quebec City, Canada, located along the north shore of the Saint Lawrence River.
  • C. Oakboro
    Oakboro is a small town located in Stanly County in the U.S. state of North Carolina.
  • D. Poquoson
    Poquoson is an independent, coastal city in southeastern Virginia known for its small-town character, maritime heritage, and location along the Chesapeake Bay.
  • E. Upland Borough
    Upland Borough is a small municipality in Delaware County, Pennsylvania, known primarily as a residential community within the greater Philadelphia metropolitan area.
  • 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_69d81c6543a48190bd5ba93d7419e797 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2fa830ac81908cb7df7c9e81e42a completed April 14, 2026, 12:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbc333b7a08190b4f121fef69f7513 completed May 6, 2026, 10:39 p.m.
Created at: April 9, 2026, 10:20 p.m.