Triple

T1563505
Position Surface form Disambiguated ID Type / Status
Subject Sena dynasty E33379 entity
Predicate notableRuler P22 FINISHED
Object Keshava Sena E182309 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: Keshava Sena | Statement: [Sena dynasty, notableRuler, Keshava Sena]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keshava Sena
Context triple: [Sena dynasty, notableRuler, Keshava Sena]
  • A. Damodar Rao
    Damodar Rao was the adopted son and heir of Rani Lakshmibai of Jhansi, a key figure in the events surrounding the Indian Rebellion of 1857.
  • B. Madhusudan
    Madhusudan is the literary pseudonym of Michael Madhusudan Dutt, a pioneering 19th-century Bengali poet and dramatist known for modernizing Bengali literature.
  • C. Hemanta Sena chosen
    Hemanta Sena was an early medieval Indian ruler who established the Sena dynasty, which became a major power in Bengal.
  • D. Fakir Mohan Senapati
    Fakir Mohan Senapati was a pioneering Odia novelist and short-story writer, often regarded as the father of modern Odia literature.
  • E. Ishvarakrishna
    Ishvarakrishna was an influential Indian philosopher best known for composing the *Samkhyakarika*, the foundational classical text of the Samkhya school of Hindu philosophy.
  • 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_69a885ef9cf48190b0af0f5ce3d02231 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a9089c7b9881909e44fee8053ac189 completed March 5, 2026, 4:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad608813548190b156fb9470ed3239 completed March 8, 2026, 11:42 a.m.
Created at: March 4, 2026, 7:27 p.m.