Triple

T20053907
Position Surface form Disambiguated ID Type / Status
Subject Vishnu Parva E499276 entity
Predicate relatedWork P37 FINISHED
Object Bhavishya Parva 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: Bhavishya Parva | Statement: [Vishnu Parva, relatedWork, Bhavishya Parva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bhavishya Parva
Context triple: [Vishnu Parva, relatedWork, Bhavishya Parva]
  • A. Bhavishya Parva chosen
    Bhavishya Parva is a section of the Harivamsa that focuses on future events, prophecies, and eschatological themes within the broader narrative of Hindu mythology.
  • B. Bhishma-parvan
    Bhishma-parvan is a book of the Indian epic Mahabharata that primarily narrates the early battles of the Kurukshetra war under the command of the grandsire Bhishma.
  • C. Aishika Parva
    Aishika Parva is a section of the Indian epic Mahabharata that continues the narrative following the events of the Sauptika Parva.
  • D. Virata Parva
    Virata Parva is a book of the Indian epic Mahabharata that narrates the Pandavas’ year of incognito exile in the kingdom of Virata.
  • E. Krishnavatara
    Krishnavatara is a celebrated multi-volume historical novel series by K. M. Munshi that retells the life and legends of Lord Krishna in a richly narrative form.
  • 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_69da6276bcf48190aabbf279192a5fb4 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66331c7488190840d43792ff09977 completed April 20, 2026, 5:32 p.m.
Created at: April 11, 2026, 3:38 p.m.