Triple

T5075989
Position Surface form Disambiguated ID Type / Status
Subject Trialeti Range E114396 entity
Predicate near P350 FINISHED
Object Borjomi E111927 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: Borjomi | Statement: [Trialeti Range, near, Borjomi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Borjomi
Context triple: [Trialeti Range, near, Borjomi]
  • A. Borjomi chosen
    Borjomi is a Georgian resort town famous for its mineral water springs and scenic location in the Borjomi Gorge.
  • B. Tskaltubo
    Tskaltubo is a spa town in western Georgia renowned for its radon-carbonate mineral springs and Soviet-era sanatoriums.
  • C. Bolnisi
    Bolnisi is a town in southern Georgia known for its historic Bolnisi Sioni Cathedral and its diverse cultural heritage.
  • D. Gudauri
    Gudauri is a popular ski resort town in the Greater Caucasus Mountains of Georgia, known for its high-altitude slopes and freeride opportunities.
  • E. Borjomi Gorge
    Borjomi Gorge is a scenic river valley in central Georgia known for its mineral springs, dense forests, and role as a key natural corridor within the Borjomi region.
  • 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_69bd443dbf908190a9401e9c2dc7bd7d completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd74d3b0088190a658864cb120eef4 completed March 20, 2026, 4:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69beb121fa388190ab3909d20f014b6f completed March 21, 2026, 2:54 p.m.
Created at: March 20, 2026, 1:39 p.m.