Triple

T17309323
Position Surface form Disambiguated ID Type / Status
Subject Nome, Alaska E420249 entity
Predicate hasHarbor P3007 FINISHED
Object Nome Harbor E469725 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: Nome Harbor | Statement: [Nome, Alaska, hasHarbor, Nome Harbor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nome Harbor
Context triple: [Nome, Alaska, hasHarbor, Nome Harbor]
  • A. Nome Harbor chosen
    Nome Harbor is a small but vital Arctic seaport on Alaska’s western coast, serving as the primary maritime access point for the remote city of Nome and nearby communities.
  • B. Marion Harbor
    Marion Harbor is a coastal harbor in Marion, Massachusetts, known for its sheltered waters, boating, and scenic New England shoreline.
  • C. Savannah Harbor
    Savannah Harbor is a major Atlantic seaport and shipping hub serving the city of Savannah, Georgia, and the surrounding southeastern United States.
  • D. Weno Harbor
    Weno Harbor is the main maritime harbor serving the island town of Weno in Chuuk State, Micronesia, functioning as a key hub for local transportation and trade.
  • E. Accabonac Harbor
    Accabonac Harbor is a coastal estuary and scenic natural area on the East End of Long Island, known for its rich wildlife habitat and protected wetlands.
  • 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_69d889d22b848190a4663d0b8f8f76e7 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e439970cf08190bc9e49ba830da0d9 completed April 19, 2026, 2:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0180e30934819087b7c838c8874aff completed May 11, 2026, 7:10 a.m.
Created at: April 10, 2026, 5:43 a.m.