Triple

T23529672
Position Surface form Disambiguated ID Type / Status
Subject Kornati Islands E576527 entity
Predicate hasPart P35 FINISHED
Object Smokvica Vela 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: Smokvica Vela | Statement: [Kornati Islands, hasPart, Smokvica Vela]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Smokvica Vela
Context triple: [Kornati Islands, hasPart, Smokvica Vela]
  • A. Smokvica Vela chosen
    Smokvica Vela is an uninhabited Adriatic island in Croatia, situated within the protected waters and rugged archipelago of Kornati National Park.
  • B. Smokvica
    Smokvica is a small village and wine-producing settlement located on the island of Korčula in Croatia.
  • C. Smokvica
    Smokvica is a village located in the Gevgelija region of southeastern North Macedonia.
  • D. Smokvica Pag
    Smokvica Pag is a small Croatian island in the Adriatic Sea, situated within the Pag archipelago and known for its uninhabited, rugged coastline and clear waters.
  • E. Veliki Crljeni
    Veliki Crljeni is a suburban settlement in the Lazarevac municipality near Belgrade, Serbia, known for its proximity to regional coal mining and energy facilities.
  • 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_69e245f5a8848190a2ba42e271c6c31f completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f1ac7646a48190b5dcbaf8c0c194df completed April 29, 2026, 7 a.m.
Created at: April 17, 2026, 6:09 p.m.