Triple

T21863392
Position Surface form Disambiguated ID Type / Status
Subject Mahon harbour E539821 entity
Predicate hasIsland P970 FINISHED
Object King’s 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: King’s Island | Statement: [Mahon harbour, hasIsland, King’s Island]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: King’s Island
Context triple: [Mahon harbour, hasIsland, King’s Island]
  • A. King's Island chosen
    King's Island is the historic core of Limerick city, Ireland, known for landmarks like King John’s Castle and its medieval streetscape.
  • B. Kings Island
    Kings Island is a large amusement and theme park in Mason, Ohio, known for its roller coasters and family attractions.
  • C. Kings Dominion
    Kings Dominion is a large amusement and theme park in Doswell, Virginia, known for its roller coasters and family attractions.
  • D. Phantasialand
    Phantasialand is a major German theme park known for its highly themed lands and innovative roller coasters and attractions.
  • E. Knott's Berry Farm
    Knott's Berry Farm is a historic theme park in Southern California known for its roller coasters, family attractions, and origins as a berry farm and roadside restaurant.
  • 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_69e0c47829648190bbe2d1d7033768ec completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f0d63d927c8190bcfccc140357484c completed April 28, 2026, 3:46 p.m.
Created at: April 16, 2026, 6:56 p.m.