Triple
T22590987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pillaiyar |
E564948
|
entity |
| Predicate | hasOtherName |
P39
|
FINISHED |
| Object | Vighneshvara |
—
|
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: Vighneshvara | Statement: [Pillaiyar, hasOtherName, Vighneshvara]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vighneshvara Context triple: [Pillaiyar, hasOtherName, Vighneshvara]
-
A.
Vighneshvara
chosen
Vighneshvara is a prominent form of the Hindu god Ganesha, revered as the remover of obstacles and patron of beginnings and wisdom.
-
B.
Someshvara
Someshvara was a medieval Indian king of the Chauhan (Chahamana) dynasty, remembered as one of its prominent rulers in northwestern India.
-
C.
Nandikeshvara
Nandikeshvara is a revered figure in Hindu tradition, often identified with Nandi, the divine bull and devoted gatekeeper and attendant of the god Shiva.
-
D.
Mahadev
Mahadev is the naive yet well-meaning aspiring writer who serves as the central protagonist and narrator in the satirical Hindi film "Welcome to Sajjanpur."
-
E.
Devanur Mahadeva
Devanur Mahadeva is a prominent Indian writer and public intellectual known for his socially conscious and Dalit-centered works in Kannada.
- 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_69e245836014819091b91ed3074742a3 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f16160651081909d23735336fd7a16 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 2:48 p.m.