Triple

T10805982
Position Surface form Disambiguated ID Type / Status
Subject Zeravshan River E254965 entity
Predicate region P40 FINISHED
Object Samarkand Region E334666 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: Samarkand Region | Statement: [Zeravshan River, region, Samarkand Region]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Samarkand Region
Context triple: [Zeravshan River, region, Samarkand Region]
  • A. Samarkand Region chosen
    Samarkand Region is an administrative region in eastern Uzbekistan best known for encompassing the historic Silk Road city of Samarkand.
  • B. Bukhara Region
    Bukhara Region is an administrative region in southwestern Uzbekistan known for its historic Silk Road city of Bukhara and its vast expanses of the Kyzylkum Desert.
  • C. Khorezm Region
    Khorezm Region is an administrative region in northwestern Uzbekistan, historically part of the ancient Khwarezm civilization and centered around the city of Urgench.
  • D. Fergana Region
    Fergana Region is an administrative region in eastern Uzbekistan known for its fertile Fergana Valley, dense population, and significant agricultural and industrial output.
  • E. Andijan Region
    Andijan Region is an administrative region in eastern Uzbekistan known for its dense population, fertile Fergana Valley agriculture, and the city of Andijan as its capital.
  • 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_69d6aa61c15c8190a1839550c56e75e1 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d733b3f92c8190bcc85db22d77bb7d completed April 9, 2026, 5:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69de5680566c8190bd4ce7a736dc0e46 completed April 14, 2026, 3 p.m.
Created at: April 8, 2026, 9:18 p.m.