Triple
T20412783
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kamakshi Amman Temple |
E500630
|
entity |
| Predicate | dedicatedTo |
P500
|
FINISHED |
| Object | Parvati |
—
|
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: Parvati | Statement: [Kamakshi Amman Temple, dedicatedTo, Parvati]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Parvati Context triple: [Kamakshi Amman Temple, dedicatedTo, Parvati]
-
A.
Devi Shachi
Devi Shachi, also known as Indrani, is the queen of the gods and consort of Indra in Hindu mythology, revered as a powerful goddess of beauty, prosperity, and divine authority.
-
B.
Goddess Vindhyavasini
Goddess Vindhyavasini is a revered Hindu manifestation of the Divine Mother, worshipped especially in the Vindhyachal region as a powerful and protective form of Durga.
-
C.
Kamakshi
chosen
Kamakshi is a revered form of the Hindu goddess Parvati, worshipped especially in Kanchipuram as a central deity of Shakta tradition.
-
D.
Bagalamukhi
Bagalamukhi is a Hindu goddess and one of the ten Mahavidyas, revered for her power to paralyze enemies and silence negative forces.
-
E.
Padma Parvati Lakshmi
Padma Parvati Lakshmi is an Indian-American author, model, and television host best known for presenting the cooking competition show "Top Chef."
- 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_69e0b4a935588190b9446a99b37ced44 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67a417f208190be9bc11650ee0a87 |
completed | April 20, 2026, 7:10 p.m. |
Created at: April 16, 2026, 11:30 a.m.