Triple
T20342722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vākyapadīya |
E495780
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Vākya-kāṇḍa |
—
|
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: Vākya-kāṇḍa | Statement: [Vākyapadīya, hasPart, Vākya-kāṇḍa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vākya-kāṇḍa Context triple: [Vākyapadīya, hasPart, Vākya-kāṇḍa]
-
A.
Vākya-kāṇḍa
chosen
Vākya-kāṇḍa is the section of the Sanskrit grammatical-philosophical treatise Vākyapadīya that focuses on the theory and analysis of sentences and their meaning.
-
B.
Prakīrṇaka-kāṇḍa
Prakīrṇaka-kāṇḍa is one of the major sections of the Sanskrit grammatical-philosophical treatise Vākyapadīya, dealing with various miscellaneous topics in language and meaning.
-
C.
Anubhashya
Anubhashya is a Sanskrit commentary on the Brahma Sutras composed by the Hindu philosopher Vallabhacharya, foundational to the Pushtimarg (Path of Grace) tradition.
-
D.
Astika sub-parva
Astika sub-parva is a section of the Indian epic Mahabharata that narrates the story of the sage Astika and the halting of King Janamejaya’s snake sacrifice.
-
E.
Sangraha sub-parva
Sangraha sub-parva is a section of the Indian epic Mahabharata that provides an overview and summary of the stories and events to be narrated in the larger work.
- 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_69e0b4a3320881909495ae8bc30bc2dc |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67836b72081908be65115abdb37bf |
completed | April 20, 2026, 7:02 p.m. |
Created at: April 16, 2026, 11:24 a.m.