Triple

T20930030
Position Surface form Disambiguated ID Type / Status
Subject Maratha region E515445 entity
Predicate hasSubregion P285 FINISHED
Object Desh NE NERFINISHED

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: Desh | Statement: [Maratha region, hasSubregion, Desh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Desh
Context triple: [Maratha region, hasSubregion, Desh]
  • A. Desh chosen
    Desh is a historical region in western Maharashtra, India, known for its cultural significance and role in the Maratha heartland.
  • B. Desh
    Desh is a critically acclaimed solo dance-theatre work by British-Bangladeshi choreographer Akram Khan that explores identity, memory, and homeland.
  • C. Desiya
    Desiya is a regional dialect spoken in parts of Odisha, India, influenced by Odia and neighboring tribal and Indo-Aryan languages.
  • D. Negara
    Negara is a town in western Bali, Indonesia, known as an administrative and commercial center in the Jembrana Regency.
  • E. Deesa
    Deesa is a town in the Banaskantha district of Gujarat, India, known historically as a former princely state and for its nearby military air base.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4fb431c8190b9d40e6a72f0cc87 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6f6545f8c81908a8c2f0e8d7b060e completed April 21, 2026, 4 a.m.
Created at: April 16, 2026, 12:49 p.m.