Triple
T4522927
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kubera |
E103309
|
entity |
| Predicate | nameVariant |
P744
|
FINISHED |
| Object | Kuvera |
E103309
|
NE FINISHED |
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: Kuvera | Statement: [Kubera, nameVariant, Kuvera]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kuvera Context triple: [Kubera, nameVariant, Kuvera]
-
A.
Kubera
chosen
Kubera is the Hindu god of wealth and the treasurer of the gods, revered as the lord of riches and prosperity.
-
B.
Kamsa
Kamsa is a tyrannical king in Hindu mythology, best known as the evil uncle and nemesis of Lord Krishna.
-
C.
Kunjara
Kunjara is an alternative name for the Fur language spoken by the Fur people of western Sudan.
-
D.
Mularaja
Mularaja was the 10th-century founder of the Chaulukya (Solanki) dynasty in Gujarat, India, known for his patronage of major temples including the famed Somnath Temple.
-
E.
Pavanputra
Pavanputra is a revered epithet of the Hindu deity Hanuman, highlighting his divine parentage as the son of the wind god.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69bd43dba59881908cf59b31df8c7ae1 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd574d7c2481909049955ca47613a6 |
completed | March 20, 2026, 2:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bda440e104819095d84fcd183c7a44 |
completed | March 20, 2026, 7:47 p.m. |
Created at: March 20, 2026, 1:02 p.m.