Triple

T21418612
Position Surface form Disambiguated ID Type / Status
Subject Rama E528371 entity
Predicate children P980 FINISHED
Object Kusha 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: Kusha | Statement: [Rama, children, Kusha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kusha
Context triple: [Rama, children, Kusha]
  • A. Kusha chosen
    Kusha is a figure from the Hindu epic Ramayana, traditionally regarded as one of the twin sons of Rama and Sita and a ruler in the Ikshvaku dynasty.
  • B. Upamanyu
    Upamanyu is a devoted disciple in ancient Indian literature, known from the Mahabharata for his exemplary obedience and perseverance in serving his guru.
  • C. Rukmi
    Rukmi is a character in Hindu mythology known as the proud and antagonistic brother of Rukmini, who opposed her marriage to Krishna.
  • D. Chyavana
    Chyavana is an ancient Vedic sage renowned in Hindu tradition for his rejuvenation legend and association with the formulation of the Ayurvedic tonic Chyawanprash.
  • E. Aloysya
    Aloysya is a given name, typically a feminine variant of Aloysius, used in various cultures and languages.
  • 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_69e0c454c248819093425d1099101c09 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ee62d29f948190b820c92014d1c53a completed April 26, 2026, 7:09 p.m.
Created at: April 16, 2026, 5:46 p.m.