Triple

T20998300
Position Surface form Disambiguated ID Type / Status
Subject Mitkof Island E517208 entity
Predicate hasPort P35 FINISHED
Object Petersburg Harbor 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: Petersburg Harbor | Statement: [Mitkof Island, hasPort, Petersburg Harbor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Petersburg Harbor
Context triple: [Mitkof Island, hasPort, Petersburg Harbor]
  • A. Petersburg harbor chosen
    Petersburg harbor is the main fishing and maritime harbor serving the small coastal community of Petersburg on Mitkof Island in Southeast Alaska.
  • B. Cape Charles Harbor
    Cape Charles Harbor is a coastal harbor on Virginia’s Eastern Shore that serves as a key recreational and commercial waterfront for the town of Cape Charles.
  • C. Port of Virginia
    The Port of Virginia is a major U.S. East Coast seaport and global shipping hub centered in the Hampton Roads region of Virginia.
  • D. Annapolis Harbor
    Annapolis Harbor is a historic waterfront and marina area in Annapolis, Maryland, known for its sailing, maritime heritage, and proximity to the U.S. Naval Academy.
  • E. Portland harbor
    Portland harbor is a major seaport on the coast of Maine known historically as a key commercial and transportation hub in New England.
  • 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_69e0b5006e2881909fc2383f841740cc completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fc22ca6081908bf054ddcfea9e19 completed April 21, 2026, 4:25 a.m.
Created at: April 16, 2026, 1:51 p.m.