Triple
T20202452
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harivamsa |
E493257
|
entity |
| Predicate | traditionallyAttributedTo |
P6838
|
FINISHED |
| Object | Vyasa |
—
|
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: Vyasa | Statement: [Harivamsa, traditionallyAttributedTo, Vyasa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vyasa Context triple: [Harivamsa, traditionallyAttributedTo, Vyasa]
-
A.
Vyasa
chosen
Vyasa is the legendary sage in Hindu tradition credited with composing and compiling the Mahabharata and organizing the Vedas.
-
B.
Kumara Vyasa
Kumara Vyasa was a renowned medieval Kannada poet best known for his epic retelling of the Mahabharata, "Karnata Bharata Kathamanjari."
-
C.
Vaishampayana
Vaishampayana is an ancient sage and disciple of Vyasa, best known in Hindu tradition for reciting and transmitting the Mahabharata.
-
D.
Valmiki
Valmiki is the revered ancient Indian sage traditionally credited with composing the epic Sanskrit poem Ramayana.
-
E.
Bādarāyaṇa
Bādarāyaṇa is an ancient Indian sage traditionally credited with authoring the Brahma Sūtras, a foundational text of the Vedānta school of Hindu philosophy.
- 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_69da6269614c8190bb40475d9d477358 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66d8ec73c8190b630599c5ceb22ac |
completed | April 20, 2026, 6:16 p.m. |
Created at: April 11, 2026, 11:37 p.m.