Triple

T31645867
Position Surface form Disambiguated ID Type / Status
Subject Candrakīrti E807580 entity
Predicate Prasannapadā_type P172058 FINISHED
Object commentary on Nāgārjuna’s Mūlamadhyamakakārikā LITERAL FINISHED

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: commentary on Nāgārjuna’s Mūlamadhyamakakārikā | Statement: [Candrakīrti, Prasannapadā_type, commentary on Nāgārjuna’s Mūlamadhyamakakārikā]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: Prasannapadā_type
Context triple: [Candrakīrti, Prasannapadā_type, commentary on Nāgārjuna’s Mūlamadhyamakakārikā]
  • A. दोषसिद्धि
    Indicates a judicial relationship where an authority formally establishes and declares a person’s guilt for an alleged offense.
  • B. abhidharmaText
    Indicates a relationship where a text is classified as or associated with Abhidharma literature within the Buddhist doctrinal corpus.
  • C. inSamkhya
    Indicates that something is situated within, belongs to, or is characterized as part of the Sāṃkhya philosophical system or framework.
  • D. associatedUpanishad
    Indicates a relationship where something is linked or connected to a particular Upanishad as its source, reference, or context.
  • E. VajranabhaIs
    Indicates that something or someone is identified as or characterized by being Vajranabha.
  • F. None of above. chosen

Provenance (4 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_69f348d9ce58819093ea2da83cbeeec1 completed April 30, 2026, 12:19 p.m.
NER Named-entity recognition batch_69f6a956e9b08190bf83547bba8e8147 completed May 3, 2026, 1:48 a.m.
PD Predicate disambiguation batch_69f6a757c6e081908e37631e5d8d246b completed May 3, 2026, 1:39 a.m.
PDg Predicate description generation batch_69f6a8036ab481908019f2f071fa406e completed May 3, 2026, 1:42 a.m.
Created at: April 30, 2026, 10:51 p.m.