Triple

T23501423
Position Surface form Disambiguated ID Type / Status
Subject Sauvie Island E571855 entity
Predicate hasHistoricalName P2834 FINISHED
Object Wapato Island 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: Wapato Island | Statement: [Sauvie Island, hasHistoricalName, Wapato Island]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wapato Island
Context triple: [Sauvie Island, hasHistoricalName, Wapato Island]
  • A. Wapato Island chosen
    Wapato Island is the historical name for Sauvie Island, a large, agriculturally rich island in the Columbia River near Portland, Oregon.
  • B. Nashawena Island
    Nashawena Island is one of the Elizabeth Islands off the coast of Massachusetts, known for its largely undeveloped landscape and private ownership.
  • C. Lummi Island
    Lummi Island is a small, rural island in the Salish Sea of Washington State known for its scenic landscapes, quiet community, and access via ferry from the mainland.
  • D. Yallock Island
    Yallock Island is a small island located within Western Port, a large tidal bay in southern Victoria, Australia.
  • E. Kane Island
    Kane Island is a small island located within Wabigoon Lake in northwestern Ontario, Canada.
  • 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_69e245b4829881909b77a70e942bbd54 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a8fd65e08190ae94ad4f0638cc0e completed April 29, 2026, 6:45 a.m.
Created at: April 17, 2026, 6:06 p.m.