Triple

T22474834
Position Surface form Disambiguated ID Type / Status
Subject Swan Islands E555601 entity
Predicate hasIsland P970 FINISHED
Object Little Swan 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: Little Swan Island | Statement: [Swan Islands, hasIsland, Little Swan Island]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Little Swan Island
Context triple: [Swan Islands, hasIsland, Little Swan Island]
  • A. Fairy Island
    Fairy Island is a small, picturesque island located within Lake Mahopac in New York, known for its scenic and tranquil setting.
  • B. Fairy Island
    Fairy Island is a small, scenic island located in Ontario’s Lake Rosseau, a popular cottage-country and boating destination in Muskoka.
  • C. Swan Island
    Swan Island is a small island whose scenic views are prominently visible from the nearby vantage point known as Overlook.
  • D. Swan’s Island
    Swan’s Island is a small, sparsely populated island community off the coast of Maine, known for its traditional fishing heritage, scenic coastal landscapes, and quiet, rural character.
  • E. Great Swan Island chosen
    Great Swan Island is the larger of the Swan Islands in the Caribbean Sea, known for its remote location and use as a strategic and meteorological outpost.
  • 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_69e11e52c2048190952dc5df209b9bed completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15be2d5388190a59d11b3403d998b completed April 29, 2026, 1:16 a.m.
Created at: April 16, 2026, 8:49 p.m.