Triple
T20810903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mandodari |
E512296
|
entity |
| Predicate | motherOf |
P120
|
FINISHED |
| Object | Akshayakumara |
—
|
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: Akshayakumara | Statement: [Mandodari, motherOf, Akshayakumara]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Akshayakumara Context triple: [Mandodari, motherOf, Akshayakumara]
-
A.
Akshayakumara
chosen
Akshayakumara is a lesser-known son of the demon king Ravana in the Hindu epic Ramayana, noted for being slain by the monkey-warrior Hanuman during the siege of Lanka.
-
B.
Vishnukumara
Vishnukumara was a 10th-century Khmer official associated with the construction and patronage of the intricately carved Banteay Srei temple in Cambodia.
-
C.
Shanmukha
Shanmukha is a revered Hindu deity of war and victory, widely worshipped as the six-faced son of Shiva and Parvati.
-
D.
Mahadeva
Mahadeva is a principal form of the Hindu god Shiva, revered as the supreme deity and great lord in Shaivism.
-
E.
Shankara
Shankara is a revered epithet of the Hindu god Shiva, highlighting his role as a benevolent and auspicious divine benefactor.
- 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_69e0b4cd25088190b48ca9700cd24efc |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2d27a4881908b34679385d8b94b |
completed | April 21, 2026, 12:20 a.m. |
Created at: April 16, 2026, 12:40 p.m.