Triple
T20446740
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anandavardhana |
E501535
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Dhvanyaloka |
—
|
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: Dhvanyaloka | Statement: [Anandavardhana, notableWork, Dhvanyaloka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dhvanyaloka Context triple: [Anandavardhana, notableWork, Dhvanyaloka]
-
A.
Dhvanyāloka
chosen
Dhvanyāloka is a foundational Sanskrit treatise on literary theory and poetics, especially known for formulating the influential doctrine of poetic suggestion (dhvani).
-
B.
Varuṇaloka
Varuṇaloka is the mythological celestial realm associated with the Vedic deity Varuna, often envisioned as his divine oceanic or watery domain.
-
C.
Nisargadhama
Nisargadhama is a scenic river island and eco-tourism spot in Karnataka, India, known for its lush forests, bamboo groves, and wildlife.
-
D.
Nagaloka
Nagaloka is the mythological subterranean realm in Hindu and Buddhist cosmology that serves as the domain of serpentine beings known as nagas.
-
E.
Bhavantarana
Bhavantarana is an Indian experimental film by director Kumar Shahani that explores classical Odissi dance and its spiritual, cultural dimensions through a highly stylized, non-narrative form.
- 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_69e0b4ac0a1c81908845d0f8a56abce8 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e68cfe57a8819094bd3d324bd567f5 |
completed | April 20, 2026, 8:30 p.m. |
Created at: April 16, 2026, 11:32 a.m.