Triple

T236946
Position Surface form Disambiguated ID Type / Status
Subject Assam E4843 entity
Predicate capital P234 FINISHED
Object Dispur E30588 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: Dispur | Statement: [Assam, capital, Dispur]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dispur
Context triple: [Assam, capital, Dispur]
  • A. Guwahati chosen
    Guwahati is a major city in northeastern India, serving as a key cultural, economic, and transportation hub for the region.
  • B. Calcutta
    Calcutta, now known as Kolkata, is a major cultural and commercial metropolis in eastern India that served as the capital of British India until the early 20th century.
  • C. Dibrugarh
    Dibrugarh is a prominent city in northeastern India known as a major commercial and industrial hub of Assam, especially for its tea industry and oil and natural gas sectors.
  • D. Chandigarh
    Chandigarh is a planned city in northern India, renowned for its modernist architecture and urban design largely conceived by the Swiss-French architect Le Corbusier.
  • E. Jorhat
    Jorhat is a prominent city in northeastern India known as a cultural and educational hub and a key center of the tea industry in Assam.
  • 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_69a257c3d0708190b0871c4269d273e6 completed Feb. 28, 2026, 2:49 a.m.
NER Named-entity recognition batch_69a25ccc5d548190b505bf1d99db41bd completed Feb. 28, 2026, 3:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69a3e01015108190b617592019306e39 completed March 1, 2026, 6:43 a.m.
Created at: Feb. 28, 2026, 2:53 a.m.