Triple

T20354525
Position Surface form Disambiguated ID Type / Status
Subject Ruma E496106 entity
Predicate mentionedIn P831 FINISHED
Object KishkindhaKanda 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: KishkindhaKanda | Statement: [Ruma, mentionedIn, KishkindhaKanda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KishkindhaKanda
Context triple: [Ruma, mentionedIn, KishkindhaKanda]
  • A. Kishkindha Kanda chosen
    Kishkindha Kanda is the fourth book of the ancient Indian epic Ramayana, focusing on Rama’s alliance with the monkey king Sugriva and the search for Sita.
  • B. Aranya Kanda
    Aranya Kanda is the third book of the ancient Indian epic Ramayana, focusing on Rama’s exile in the forest and the abduction of Sita by Ravana.
  • C. Kamba Ramayanam
    Kamba Ramayanam is a 12th-century Tamil epic poem by the poet Kambar that retells the Sanskrit Ramayana with rich devotional and literary embellishments.
  • D. Kiranavali
    Kiranavali is a philosophical treatise attributed to the Indian logician Udayana, known for its contributions to classical Nyāya thought.
  • E. Sundara Kanda
    Sundara Kanda is a major book of the Indian epic Ramayana that focuses on Hanuman’s journey to Lanka and his pivotal role in the search for Sita.
  • 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_69e0b4a3f7f48190b37f354574028ca6 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67852ca9881908a5af18005639859 completed April 20, 2026, 7:02 p.m.
Created at: April 16, 2026, 11:25 a.m.