Triple
T20777393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sharada Peeth |
E511388
|
entity |
| Predicate | dedicatedTo |
P500
|
FINISHED |
| Object | Goddess Saraswati |
—
|
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: Goddess Saraswati | Statement: [Sharada Peeth, dedicatedTo, Goddess Saraswati]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Goddess Saraswati Context triple: [Sharada Peeth, dedicatedTo, Goddess Saraswati]
-
A.
Goddess Saraswati
chosen
Goddess Saraswati is the Hindu deity of knowledge, wisdom, music, arts, and learning, often depicted in white attire with a veena and a book.
-
B.
Goddess Sharada
Goddess Sharada is a revered Hindu deity of wisdom, learning, and the arts, venerated as a form of Saraswati and especially worshipped at the Sringeri Sharada Peetham in Karnataka, India.
-
C.
Goddess Savitri
Goddess Savitri is a Vedic solar deity revered as the personified divine light and wisdom invoked in the Gayatri Mantra.
-
D.
Gayatri
Gayatri is a highly revered Vedic poetic meter consisting of three lines of eight syllables each, widely used in Hindu sacred hymns and mantras.
-
E.
Bagalamukhi
Bagalamukhi is a Hindu goddess and one of the ten Mahavidyas, revered for her power to paralyze enemies and silence negative forces.
- 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_69e0b4cac7a48190a715cb3d545df2b4 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c26bbe108190bb7c3e5b416e44fe |
completed | April 21, 2026, 12:18 a.m. |
Created at: April 16, 2026, 12:37 p.m.