Triple

T20080908
Position Surface form Disambiguated ID Type / Status
Subject Ambalika E499997 entity
Predicate sibling P363 FINISHED
Object Ambika 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: Ambika | Statement: [Ambalika, sibling, Ambika]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ambika
Context triple: [Ambalika, sibling, Ambika]
  • A. Ambika chosen
    Ambika is a queen in the Indian epic Mahabharata, known as one of the wives of King Vichitravirya and the mother of the Kuru king Dhritarashtra.
  • B. Anuradha
    Anuradha is a 1960 Indian Hindi-language romantic drama film, acclaimed for its sensitive storytelling and music, directed by Hrishikesh Mukherjee and starring Balraj Sahni and Leela Naidu.
  • C. Anuradha
    Anuradha is a Vedic astrology lunar mansion (nakshatra) associated with qualities of devotion, discipline, and success in partnerships.
  • D. Anamika
    Anamika is a notable creative work associated with Kamal Bose, recognized for its significance in his career.
  • E. Anasuya
    Anasuya is a revered sage and exemplar of chastity and devotion in Hindu tradition, celebrated as the wife of the rishi Atri and mother of the divine Trimurti incarnations.
  • 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_69da627770948190997f486f9a2e370f completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66557c19c8190b511857490bbd423 completed April 20, 2026, 5:41 p.m.
Created at: April 11, 2026, 3:41 p.m.