Triple

T20160534
Position Surface form Disambiguated ID Type / Status
Subject Shastri E491690 entity
Predicate relatedTo P37 FINISHED
Object Shastra 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: Shastra | Statement: [Shastri, relatedTo, Shastra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shastra
Context triple: [Shastri, relatedTo, Shastra]
  • A. Meykanda Shastras
    Meykanda Shastras are foundational Tamil philosophical texts that systematically codify and expound the metaphysics and theology of Shaiva Siddhanta.
  • B. Pashupatastra
    Pashupatastra is a legendary and immensely destructive celestial weapon in Hindu mythology, associated with Lord Shiva and capable of annihilating entire worlds.
  • C. Shilpa Shastras chosen
    Shilpa Shastras are ancient Indian treatises that codify the principles, proportions, and iconography of art, sculpture, and temple architecture.
  • D. Shaastra
    Shaastra is the annual student-run technical festival of IIT Madras, known for its large-scale engineering competitions, workshops, and lectures.
  • E. Shikshapatri
    Shikshapatri is a key Hindu religious text composed by Swaminarayan that outlines moral, spiritual, and social codes of conduct for his followers.
  • 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_69da6266c6888190bc1a3ecf24814d34 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e667e43940819080f6a0b7331aaab0 completed April 20, 2026, 5:52 p.m.
Created at: April 11, 2026, 11:34 p.m.