Triple

T23217788
Position Surface form Disambiguated ID Type / Status
Subject Mahadeva E580797 entity
Predicate identifiedWith P13264 FINISHED
Object Shiva 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: Shiva | Statement: [Mahadeva, identifiedWith, Shiva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shiva
Context triple: [Mahadeva, identifiedWith, Shiva]
  • A. Shiva chosen
    Shiva is a principal Hindu god revered as the destroyer and transformer within the religion’s divine trinity, associated with asceticism, cosmic dance, and the cycle of creation and dissolution.
  • B. Mahadev
    Mahadev is the naive yet well-meaning aspiring writer who serves as the central protagonist and narrator in the satirical Hindi film "Welcome to Sajjanpur."
  • C. Vishnu
    Vishnu is a principal Hindu god revered as the preserver and protector of the universe, often depicted with blue skin and four arms and associated with avatars such as Rama and Krishna.
  • D. Ishvara
    Ishvara is the personal, manifest form of the ultimate reality in Hinduism, often understood as God with attributes who creates, sustains, and governs the universe.
  • E. Vighneshvara
    Vighneshvara is a prominent form of the Hindu god Ganesha, revered as the remover of obstacles and patron of beginnings and wisdom.
  • 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_69e2460389408190be74f41d217799a9 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f1916653f08190a7dcbc659c6b6a25 completed April 29, 2026, 5:04 a.m.
Created at: April 17, 2026, 4:08 p.m.