Triple
T20412804
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kamakshi Amman Temple |
E500630
|
entity |
| Predicate | hasShrineFor |
P27875
|
FINISHED |
| Object | Lakshmi |
—
|
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: Lakshmi | Statement: [Kamakshi Amman Temple, hasShrineFor, Lakshmi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lakshmi Context triple: [Kamakshi Amman Temple, hasShrineFor, Lakshmi]
-
A.
Sri (Lakshmi)
chosen
Sri (Lakshmi) is the Hindu goddess of wealth, prosperity, and fortune, revered as the divine consort of Lord Vishnu.
-
B.
Mahalaxmi
Mahalaxmi is a coastal neighborhood in South Mumbai, India, known for its seafront location, racecourse, and proximity to prominent religious landmarks.
-
C.
Gajalakshmi
Gajalakshmi is a revered Hindu goddess form of Lakshmi depicted with elephants flanking her, symbolizing prosperity, abundance, and royal authority.
-
D.
Lakshmi avatar
Lakshmi avatar refers to any incarnation or manifestation of the Hindu goddess Lakshmi, particularly as she appears on earth in forms such as Rukmini, the consort of Krishna.
-
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.