Triple

T20295221
Position Surface form Disambiguated ID Type / Status
Subject Anjana E505329 entity
Predicate husband P21331 FINISHED
Object Kesari 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: Kesari | Statement: [Anjana, husband, Kesari]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kesari
Context triple: [Anjana, husband, Kesari]
  • A. Kesari chosen
    Kesari is a figure in Hindu mythology known as the vanara chief and father of the deity Hanuman.
  • B. Kesari
    Kesari is a historic Marathi-language newspaper from India, founded by Bal Gangadhar Tilak, that played a key role in the Indian independence movement.
  • C. Rajkahini
    Rajkahini is a Bengali period drama film set against the backdrop of the 1947 Partition of Bengal, known for its ensemble cast of women and its exploration of displacement, violence, and identity.
  • D. Raja Hindustani
    Raja Hindustani is a popular 1996 Hindi romantic drama film starring Aamir Khan and Karisma Kapoor, known for its emotional storyline and hit music.
  • E. Padmavati
    Padmavati is a revered Hindu goddess, considered an incarnation of Lakshmi and the consort of Lord Venkateswara, widely worshipped in South India.
  • 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_69e0b4b8ab648190906e18538c250148 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6770714c4819080e3256325747ebf completed April 20, 2026, 6:57 p.m.
Created at: April 16, 2026, 11:15 a.m.