Triple

T14478297
Position Surface form Disambiguated ID Type / Status
Subject Vunisea Airport E359032 entity
Predicate locatedOn P40 FINISHED
Object Kadavu 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: Kadavu Island | Statement: [Vunisea Airport, locatedOn, Kadavu Island]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kadavu Island
Context triple: [Vunisea Airport, locatedOn, Kadavu Island]
  • A. Kadavu Islands chosen
    The Kadavu Islands are a remote volcanic archipelago in southern Fiji known for its rugged landscapes, traditional villages, and world-class coral reefs, including the Great Astrolabe Reef.
  • B. Beqa Island
    Beqa Island is a small volcanic island in Fiji known for its traditional firewalking ceremonies and surrounding coral reefs.
  • C. Malolo Island
    Malolo Island is a popular Fijian resort island in the Mamanuca archipelago, known for its beaches, coral reefs, and water-based activities.
  • D. Kolombangara Island
    Kolombangara Island is a large, nearly circular volcanic island in the Solomon Islands, notable for its central stratovolcano and World War II history.
  • E. Vangunu Island
    Vangunu Island is a large, volcanic island in the New Georgia group of the Solomon Islands, known for its dense rainforests, rich biodiversity, and small rural communities.
  • 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_69d827966698819082e140837737501d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de9248edb48190a74eb032aeaac027 completed April 14, 2026, 7:15 p.m.
Created at: April 10, 2026, 1:20 a.m.