Triple

T20044733
Position Surface form Disambiguated ID Type / Status
Subject Markandeya Purana E497527 entity
Predicate associatedDeity P1481 FINISHED
Object Chandi 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: Chandi | Statement: [Markandeya Purana, associatedDeity, Chandi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Chandi
Context triple: [Markandeya Purana, associatedDeity, Chandi]
  • A. Chandi chosen
    Chandi is a fierce and powerful warrior aspect of the Hindu goddess Devi, associated with the destruction of evil and protection of the righteous.
  • B. Kameshvari
    Kameshvari is a revered form of the Hindu goddess Tripura Sundari, embodying supreme beauty, desire, and cosmic sovereignty.
  • C. Gajju Mata
    Gajju Mata is a major bus terminal and transit hub in Lahore, Pakistan, serving as one end of the city’s Metrobus rapid transit line.
  • D. Kanchi
    Kanchi is a historic temple city in the Indian state of Tamil Nadu, renowned as a major center of Hindu pilgrimage and classical learning.
  • E. Goddess Chandi
    Goddess Chandi is a fierce and powerful form of the Hindu Divine Mother, revered as a warrior goddess who destroys evil and protects her devotees.
  • 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.