Triple

T4913815
Position Surface form Disambiguated ID Type / Status
Subject Mtiuleti E110298 entity
Predicate borders P224 FINISHED
Object Kartli E15356 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: Kartli | Statement: [Mtiuleti, borders, Kartli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kartli
Context triple: [Mtiuleti, borders, Kartli]
  • A. Kartli chosen
    Kartli is a historic central region of Georgia that has long been a political and cultural heartland for the Georgian people.
  • B. Shida Kartli
    Shida Kartli is a central region of Georgia known for its historical significance and agricultural production, with Gori as one of its main cities.
  • C. Kvemo Kartli
    Kvemo Kartli is a region in southeastern Georgia known for its ethnically diverse population, agricultural production, and industrial centers such as Rustavi.
  • D. Kakheti
    Kakheti is a historic region in eastern Georgia renowned as the country’s primary wine-producing area and a center of Georgian cultural heritage.
  • E. Imereti region of Georgia
    The Imereti region of Georgia is a historic western area centered around the city of Kutaisi, known for its rich cultural heritage, monasteries, caves, and scenic landscapes.
  • 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_69bd44132b94819088522d92beaadc78 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6e9f12b48190b3cb5378958d03cd completed March 20, 2026, 3:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0b069d3fc8190bac9d178a571b72d completed March 23, 2026, 3:15 a.m.
Created at: March 20, 2026, 1:29 p.m.