Triple

T6567742
Position Surface form Disambiguated ID Type / Status
Subject Shkhara E153953 entity
Predicate near P350 FINISHED
Object Ushguli E435964 NE FINISHED

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: Ushguli | Statement: [Shkhara, near, Ushguli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ushguli
Context triple: [Shkhara, near, Ushguli]
  • A. Ushguli chosen
    Ushguli is a remote highland village community in Georgia’s Svaneti region, renowned for its medieval stone towers, well-preserved Svan culture, and status as one of the highest continuously inhabited settlements in Europe.
  • 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. Urakhi
    Urakhi is a dialect of the Dargin language spoken by a subset of the Dargin people in the North Caucasus region of Russia.
  • D. Urunga
    Urunga is a small coastal town in New South Wales, Australia, known for its scenic boardwalks, estuary views, and relaxed seaside atmosphere.
  • E. Shurugwi
    Shurugwi is a mining town in central Zimbabwe known for its rich gold and chrome deposits.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c6880cb35881909b763eb0125236b9 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6ae54afd4819091ee65aca1de60a9 completed March 27, 2026, 4:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6e4275eec8190ba52fa4fb1bc64db completed March 27, 2026, 8:10 p.m.
Created at: March 27, 2026, 1:53 p.m.