Triple

T5375590
Position Surface form Disambiguated ID Type / Status
Subject Pandu E108950 entity
Predicate grandsonOf P27130 FINISHED
Object Shantanu E453692 NE FINISHED

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: Shantanu | Statement: [Pandu, grandsonOf, Shantanu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shantanu
Context triple: [Pandu, grandsonOf, Shantanu]
  • A. Shantanu chosen
    Shantanu is a legendary king of Hastinapura in the Indian epic Mahabharata, known as an ancestor of the Kauravas and Pandavas and as the husband of Ganga and Satyavati.
  • B. Nishant
    Nishant is a critically acclaimed 1975 Indian parallel cinema film directed by Shyam Benegal that explores themes of feudal oppression and social injustice in rural India.
  • C. Aniruddha
    Aniruddha is a prominent figure in Hindu mythology, known as the grandson of Krishna and a heroic member of the Yadava dynasty.
  • D. Savyasachi
    Savyasachi is a celebrated epithet of the Mahabharata hero Arjuna, highlighting his legendary ambidextrous skill in archery and combat.
  • E. Satyaki
    Satyaki is a heroic warrior and ally of the Pandavas in the Indian epic Mahabharata, renowned for his valor, loyalty, and skill in archery.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69bd440c77948190aad2a5f39b7b80f5 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd86aed2a8819089d9e699f53563db completed March 20, 2026, 5:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf334fb498819089a33be56fa47a01 completed March 22, 2026, 12:09 a.m.
Created at: March 20, 2026, 2:03 p.m.