Triple

T2260290
Position Surface form Disambiguated ID Type / Status
Subject Kaspi E50021 entity
Predicate administrativeRegion P285 FINISHED
Object Shida Kartli E7704 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: Shida Kartli | Statement: [Kaspi, administrativeRegion, Shida Kartli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shida Kartli
Context triple: [Kaspi, administrativeRegion, Shida Kartli]
  • A. Shida Kartli chosen
    Shida Kartli is a central region of Georgia known for its historical significance and agricultural production, with Gori as one of its main cities.
  • B. Kvemo Kartli
    Kvemo Kartli is a region in southeastern Georgia known for its ethnically diverse population, agricultural production, and industrial centers such as Rustavi.
  • C. Kartli
    Kartli is a historic central region of Georgia that has long been a political and cultural heartland for the Georgian people.
  • 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. Mtskheta-Mtianeti
    Mtskheta-Mtianeti is a mountainous region in northeastern Georgia known for its historic towns, including the ancient capital Mtskheta, and its role as a cultural and religious 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_69a88b01e0048190ba96431b5f990ba9 completed March 4, 2026, 7:41 p.m.
NER Named-entity recognition batch_69abc15be1288190a55c12674f4a5e03 completed March 7, 2026, 6:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69b0fc308f388190a10f79a02a867057 completed March 11, 2026, 5:22 a.m.
Created at: March 4, 2026, 7:48 p.m.