Triple

T21893067
Position Surface form Disambiguated ID Type / Status
Subject Ballal Sen E540602 entity
Predicate spouse P13 FINISHED
Object Ramadevi 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: Ramadevi | Statement: [Ballal Sen, spouse, Ramadevi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ramadevi
Context triple: [Ballal Sen, spouse, Ramadevi]
  • A. Ramadevi chosen
    Ramadevi was a queen consort of the Sena dynasty in medieval Bengal, known primarily as the wife of King Ballala Sena.
  • B. Saradadevi
    Saradadevi was the mother of Bengali playwright, musician, and artist Jyotirindranath Tagore and a member of the influential Tagore family of Bengal.
  • C. Padmavathi
    Padmavathi is a Hindu goddess revered primarily as an incarnation of Lakshmi and the consort of Lord Venkateswara, especially worshipped in South India.
  • D. Rama Devi
    Rama Devi was an Indian freedom fighter and social reformer from Odisha who played a significant role in the independence movement and in advancing women's education.
  • E. Vagdevi
    Vagdevi is a revered Hindu goddess associated with speech, wisdom, and learning, commonly identified with the goddess Saraswati.
  • 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_69e0c47a95908190ae3e19b716accb3d completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f11fc46dd481908a119cfbe26564a3 completed April 28, 2026, 8:59 p.m.
Created at: April 16, 2026, 7:06 p.m.