Triple

T20044695
Position Surface form Disambiguated ID Type / Status
Subject Markandeya Purana E497527 entity
Predicate genre P14 FINISHED
Object Purana 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: Purana | Statement: [Markandeya Purana, genre, Purana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Purana
Context triple: [Markandeya Purana, genre, Purana]
  • A. Purana chosen
    The Purana is a genre of ancient Indian literature comprising mythological narratives, cosmology, genealogies, and religious teachings central to Hindu tradition.
  • B. Puran
    Puran is a town and administrative subdivision located in Shangla District of Pakistan’s Khyber Pakhtunkhwa province.
  • C. Puran
    Puran is a masculine given name commonly used in South Asia, particularly in India and Nepal.
  • D. Purattasi
    Purattasi is a significant month in the Tamil calendar, traditionally associated with special religious observances and devotion to Lord Venkateswara.
  • E. Purana Pul
    Purana Pul is a historic bridge in Hyderabad, India, renowned as one of the city’s oldest surviving structures spanning the Musi River.
  • 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_69da627278c88190babe4297a9df1236 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e662eea09481908d1001165e9d719c completed April 20, 2026, 5:31 p.m.
Created at: April 11, 2026, 3:37 p.m.