Triple

T746648
Position Surface form Disambiguated ID Type / Status
Subject Kartli E15356 entity
Predicate contains P35 FINISHED
Object Kaspi E50021 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: Kaspi | Statement: [Kartli, contains, Kaspi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kaspi
Context triple: [Kartli, contains, Kaspi]
  • A. Kaspi chosen
    Kaspi is a town in central Georgia known as an industrial center and regional hub within the Shida Kartli area.
  • B. Middle Caspian
    Middle Caspian is the deep central basin of the Caspian Sea, situated between its northern shallow shelf and southern deep-water region.
  • C. Sea of Azov
    The Sea of Azov is a shallow inland sea in Eastern Europe connected to the Black Sea, bordered by Ukraine and Russia and known for its strategic and economic importance.
  • D. Amu Darya
    The Amu Darya is one of Central Asia’s largest and most historically significant rivers, flowing from the Pamir and Hindu Kush mountains toward the Aral Sea.
  • E. Caspian Sea
    The Caspian Sea is the world’s largest inland body of water, a landlocked saltwater lake situated between Europe and Asia and bordered by several countries including Russia, Kazakhstan, Turkmenistan, Iran, and Azerbaijan.
  • 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_69a49358aa308190adbc9b5a0a2adcf9 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a62ca1d081908e3191411f86498d completed March 1, 2026, 8:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac16f360208190affd6282a1040d9a completed March 7, 2026, 12:15 p.m.
Created at: March 1, 2026, 7:37 p.m.