Triple

T18451133
Position Surface form Disambiguated ID Type / Status
Subject Savitri E450783 entity
Predicate spouse P13 FINISHED
Object Satyavan 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: Satyavan | Statement: [Savitri, spouse, Satyavan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Satyavan
Context triple: [Savitri, spouse, Satyavan]
  • A. Satyavan chosen
    Satyavan is a virtuous prince in the Indian epic Mahabharata, best known as the husband of Savitri whose devotion wins him back from death.
  • B. Satyavrata
    Satyavrata is a figure in Hindu mythology who later becomes King Manu, the primordial man saved by the god Vishnu in his Matsya (fish) avatar during the great deluge.
  • C. Vidura
    Vidura is a wise and righteous counselor in the Mahabharata, renowned for his moral integrity and guidance to the Pandavas and the Kuru court.
  • D. Shatrughna
    Shatrughna is a prince of Ayodhya in the Hindu epic Ramayana, known as the devoted younger brother of Rama and the twin of Lakshmana.
  • E. Yayati
    Yayati is a legendary king from Hindu mythology, known as a progenitor of several royal lineages and for the tale in which he exchanges his old age with his son's youth.
  • 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_69d8d38345688190b565eac2e4cd7935 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e52648476c8190a5d8c3297d836f62 completed April 19, 2026, 7 p.m.
Created at: April 10, 2026, 11:31 a.m.