Triple

T20080889
Position Surface form Disambiguated ID Type / Status
Subject Tantripala E499996 entity
Predicate killedBy P4646 FINISHED
Object Shakuni 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: Shakuni | Statement: [Tantripala, killedBy, Shakuni]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shakuni
Context triple: [Tantripala, killedBy, Shakuni]
  • A. Shakuni chosen
    Shakuni is a key antagonist in the Indian epic Mahabharata, known as the cunning prince of Gandhara whose deceitful schemes and manipulation of dice play a central role in triggering the Kurukshetra war.
  • B. Drupada
    Drupada is a king in the Indian epic Mahabharata, best known as the ruler of Panchala and the father of Draupadi and Dhrishtadyumna.
  • C. Ugrasena
    Ugrasena is a legendary king in Hindu mythology, known as a ruler of the Yadava clan and the grandfather of Krishna.
  • D. Bhishmaka
    Bhishmaka is a king in Hindu mythology, best known as the ruler of Vidarbha and the father of Rukmini, the principal wife of Lord Krishna.
  • E. Meghnad
    Meghnad is a given name most notably associated with Indian astrophysicist Meghnad Saha, renowned for his pioneering work on thermal ionization and stellar spectra.
  • 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_69da627770948190997f486f9a2e370f completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66557c19c8190b511857490bbd423 completed April 20, 2026, 5:41 p.m.
Created at: April 11, 2026, 3:41 p.m.