Triple

T5025013
Position Surface form Disambiguated ID Type / Status
Subject Kingdom of Kakheti E112953 entity
Predicate capital P234 FINISHED
Object Telavi E182137 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: Telavi | Statement: [Kingdom of Kakheti, capital, Telavi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Telavi
Context triple: [Kingdom of Kakheti, capital, Telavi]
  • A. Telavi chosen
    Telavi is a historic city in eastern Georgia known as the cultural and economic center of the Kakheti wine-producing region.
  • B. Rustavi
    Rustavi is an industrial city in southeastern Georgia, located near the capital Tbilisi and known for its steel production and Soviet-era urban planning.
  • C. Zugdidi
    Zugdidi is a city in western Georgia that serves as the main urban and administrative center of the Samegrelo region.
  • D. Zestafoni
    Zestafoni is a town in western Georgia known as an important industrial and transportation hub, particularly for its ferroalloy plant and railway connections.
  • E. Tskhinvali
    Tskhinvali is the capital city of the breakaway region of South Ossetia in the South Caucasus, serving as its political and administrative center.
  • 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_69bd4435c2f48190be593158cbfcf8a3 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd736a0f8c819091d06275954329e9 completed March 20, 2026, 4:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf069d371c81909d87432f6bd2d506 completed March 21, 2026, 8:59 p.m.
Created at: March 20, 2026, 1:36 p.m.