Triple

T18939872
Position Surface form Disambiguated ID Type / Status
Subject Sno Fortress E463351 entity
Predicate region P40 FINISHED
Object Khevi 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: Khevi | Statement: [Sno Fortress, region, Khevi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Khevi
Context triple: [Sno Fortress, region, Khevi]
  • A. Khevi chosen
    Khevi is a historic mountainous region in northeastern Georgia, known for its dramatic gorges, high peaks, and medieval cultural heritage.
  • B. Tavaeli
    Tavaeli is a regional dialect of the Kaili language spoken by communities in Central Sulawesi, Indonesia.
  • C. Mtkvari River
    The Mtkvari River, also known as the Kura, is a major river in the South Caucasus that flows through Turkey, Georgia, and Azerbaijan before emptying into the Caspian Sea.
  • D. Chkhaveri
    Chkhaveri is a traditional Georgian grape variety known for producing distinctive, often semi-sweet rosé and red wines, particularly in western Georgia.
  • E. Gekhi River
    The Gekhi River is a smaller watercourse in the North Caucasus region that serves as a tributary within the Sunzha River basin.
  • 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_69d8dcfec90481909e926be9767e5779 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d3eae9b88190b6031c359090782a completed April 20, 2026, 7:21 a.m.
Created at: April 10, 2026, 11:59 a.m.