Triple

T5025012
Position Surface form Disambiguated ID Type / Status
Subject Kingdom of Kakheti E112953 entity
Predicate capital P234 FINISHED
Object Gremi E144383 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: Gremi | Statement: [Kingdom of Kakheti, capital, Gremi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gremi
Context triple: [Kingdom of Kakheti, capital, Gremi]
  • A. Gremi chosen
    Gremi is a historic town and former royal residence in eastern Georgia’s Kakheti region, known for its 16th-century church and fortress complex.
  • B. Gemer
    Gemer is a historical and geographical region in southern Slovakia known for its mining heritage, medieval castles, and karst landscapes.
  • C. Grimus
    Grimus is Salman Rushdie’s debut novel, a genre-blending work of science fiction and fantasy that explores themes of identity, immortality, and exile.
  • D. Gamelia
    Gamelia is an epithet associated with the Greek goddess Hera, emphasizing her role as protector of marriage and weddings.
  • E. Ganguise
    Ganguise is a watercourse in southern France that feeds the artificial reservoir known as Lac de la Ganguise.
  • 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_69be928919c08190be76549e1a41f61e completed March 21, 2026, 12:43 p.m.
Created at: March 20, 2026, 1:36 p.m.