Triple

T19730950
Position Surface form Disambiguated ID Type / Status
Subject Krishnaa E473850 entity
Predicate notableRelation P367 FINISHED
Object mother-in-law Kunti 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: mother-in-law Kunti | Statement: [Krishnaa, notableRelation, mother-in-law Kunti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: mother-in-law Kunti
Context triple: [Krishnaa, notableRelation, mother-in-law Kunti]
  • A. Kunti chosen
    Kunti is a prominent queen and matriarch in the Indian epic Mahabharata, best known as the mother of the Pandava princes.
  • B. Satyavati
    Satyavati is a pivotal queen in the Indian epic Mahabharata, known as the wife of King Shantanu and the matriarch whose lineage leads to the Kuru dynasty’s central figures.
  • C. Kaikeyi
    Kaikeyi is a pivotal queen in the Indian epic Ramayana, known for demanding Rama’s exile and securing the throne for her son Bharata.
  • D. Kaushalya
    Kaushalya is a queen of Ayodhya and the mother of Lord Rama in the ancient Indian epic Ramayana.
  • E. Yashoda
    Yashoda is the loving foster mother of the Hindu deity Krishna, revered for her deep maternal devotion and prominent role in his childhood stories.
  • 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_69d8e517ebd48190979ee76723bcfadf completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e649fbeaf081909e9356229eaf84dd completed April 20, 2026, 3:45 p.m.
Created at: April 10, 2026, 1:47 p.m.