Triple

T441109
Position Surface form Disambiguated ID Type / Status
Subject Bangalore English E10114 entity
Predicate region P40 FINISHED
Object Karnataka E29477 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: Karnataka | Statement: [Bangalore English, region, Karnataka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karnataka
Context triple: [Bangalore English, region, Karnataka]
  • A. Karnataka chosen
    Karnataka is a state in southwestern India known for its diverse languages and cultures, major tech hub Bengaluru, and rich historical and architectural heritage.
  • B. Kerala
    Kerala is a coastal state in southwestern India known for its backwaters, high literacy rate, distinctive Malayalam culture, and strong traditions in art, Ayurveda, and religious diversity.
  • C. Tamil Nadu
    Tamil Nadu is a state in southern India known for its rich Dravidian cultural heritage, classical arts, and major urban centers like Chennai.
  • D. Andhra Pradesh
    Andhra Pradesh is a state in southeastern India known for its long coastline along the Bay of Bengal, Telugu-speaking population, and major cities such as Visakhapatnam and Vijayawada.
  • E. Telangana
    Telangana is a state in south-central India known for its predominantly Telugu-speaking population, rich Deccan heritage, and capital city Hyderabad.
  • 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_69a2e8465ef481909655c681b01e2986 completed Feb. 28, 2026, 1:06 p.m.
NER Named-entity recognition batch_69a2ef2af84881909635ebbbb3465b1b completed Feb. 28, 2026, 1:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7c705090c81909590d7fe2ff37fef completed March 4, 2026, 5:45 a.m.
Created at: Feb. 28, 2026, 1:11 p.m.