Triple

T20362316
Position Surface form Disambiguated ID Type / Status
Subject Prince of Tao-Klarjeti E496811 entity
Predicate associatedWithRegion P285 FINISHED
Object Klarjeti 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: Klarjeti | Statement: [Prince of Tao-Klarjeti, associatedWithRegion, Klarjeti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Klarjeti
Context triple: [Prince of Tao-Klarjeti, associatedWithRegion, Klarjeti]
  • A. Klarjeti chosen
    Klarjeti is a historical region in southwestern Georgia, known as part of the medieval Tao-Klarjeti principality and for its early Christian monastic centers.
  • B. Zastava Koral
    The Zastava Koral, also known as the Yugo, is a compact Yugoslav/Serbian hatchback car that gained international notoriety in the 1980s as one of the most affordable and criticized vehicles sold in Western markets.
  • C. Biancorossi
    Biancorossi is the traditional nickname of Italian football club AC Monza, referring to the team’s white and red colors.
  • D. Biancorossi
    Biancorossi is the traditional nickname of Italian football club LR Vicenza, referring to the team’s white-and-red colors.
  • E. Bordo-Mavililer
    Bordo-Mavililer is the popular Turkish nickname for Trabzonspor, referring to the club’s claret and blue team colors.
  • 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_69e0b4a3f7f48190b37f354574028ca6 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6786efd2c8190821932ddcdef1a2f completed April 20, 2026, 7:03 p.m.
Created at: April 16, 2026, 11:26 a.m.