Triple

T4662821
Position Surface form Disambiguated ID Type / Status
Subject Expo 2017 E102574 entity
Predicate city P40 FINISHED
Object Astana E50521 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: Astana | Statement: [Expo 2017, city, Astana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Astana
Context triple: [Expo 2017, city, Astana]
  • A. Astana chosen
    Astana is the planned, modernist capital city of Kazakhstan, known for its futuristic architecture and rapid development since the late 20th century.
  • B. Almaty
    Almaty is the largest city and main commercial and cultural center of Kazakhstan, located in the country’s mountainous southeast.
  • C. Ürümqi
    Ürümqi is a major city in northwestern China that serves as the political, economic, and cultural center of the Xinjiang Uyghur Autonomous Region.
  • D. Atyrau
    Atyrau is a city in western Kazakhstan located near the Caspian Sea, notable for straddling the boundary between Europe and Asia and serving as a major center for the country’s oil industry.
  • E. Syktyvkar
    Syktyvkar is the capital city of the Komi Republic in northwestern Russia, known as an administrative, cultural, and economic center of the region.
  • 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_69bd43d823288190952279faa0d1d066 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd632d6150819085bab97021c0235a completed March 20, 2026, 3:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfafcd3908190aabf7975017ce337 completed March 21, 2026, 1:57 a.m.
Created at: March 20, 2026, 1:15 p.m.