Triple

T17937271
Position Surface form Disambiguated ID Type / Status
Subject Mathura prison of Kamsa E448498 entity
Predicate associatedWith P37 FINISHED
Object Balarama 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: Balarama | Statement: [Mathura prison of Kamsa, associatedWith, Balarama]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Balarama
Context triple: [Mathura prison of Kamsa, associatedWith, Balarama]
  • A. Balarama chosen
    Balarama is a major Hindu deity revered as the elder brother of Krishna, known for his immense strength and role in supporting and protecting dharma.
  • B. Mrigadava
    Mrigadava is the ancient deer park near Sarnath in India where Gautama Buddha is said to have delivered his first sermon.
  • C. Gopala
    Gopala is a pastoral form of the Hindu god Krishna, revered especially as a divine cowherd and protector of cows.
  • D. Anjaneya
    Anjaneya is another name for the Hindu deity Hanuman, revered as a symbol of strength, devotion, and selfless service.
  • E. Pradyumna
    Pradyumna is a prominent figure in Hindu mythology, known as the son of Krishna and Rukmini and considered an incarnation of the love god Kamadeva.
  • 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_69d8b9f79d14819095540856928f0e25 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4ad937f0881909d22ac8c2be9e35e completed April 19, 2026, 10:25 a.m.
Created at: April 10, 2026, 10:21 a.m.