Triple

T21491603
Position Surface form Disambiguated ID Type / Status
Subject Krbava E530250 entity
Predicate hasCapital P204 FINISHED
Object Udbina 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: Udbina | Statement: [Krbava, hasCapital, Udbina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Udbina
Context triple: [Krbava, hasCapital, Udbina]
  • A. Udbina chosen
    Udbina is a small town in the Lika region of Croatia, known for its historical significance and proximity to the Krbava field.
  • B. Ushba
    Ushba is a striking double-summited peak in the Caucasus Mountains of Georgia, renowned among climbers for its technical difficulty and dramatic, spire-like profile.
  • C. Ubakala
    Ubakala is a town in Abia State, southeastern Nigeria, serving as the administrative center of the Umuahia South Local Government Area.
  • D. Nabua
    Nabua is a residential suburb of Suva in Fiji, known for its local communities, schools, and proximity to central urban amenities.
  • E. Uduk
    Uduk are an indigenous ethnic group of northeastern Africa, primarily inhabiting the border regions of Sudan and Ethiopia, known for their distinct language and traditional agro-pastoral lifestyle.
  • 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_69e0c45bd15481909fba5910765cdda2 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea3ba2fc81909638bbb3e1d92ea5 completed April 23, 2026, 9:45 a.m.
Created at: April 16, 2026, 6:22 p.m.