Triple
T27697367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sundareswarar shrine |
E698333
|
entity |
| Predicate | hasGuardianDeities |
P116883
|
FINISHED |
| Object | various attendant deities of Shiva |
—
|
LITERAL 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: various attendant deities of Shiva | Statement: [Sundareswarar shrine, hasGuardianDeities, various attendant deities of Shiva]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGuardianDeities Context triple: [Sundareswarar shrine, hasGuardianDeities, various attendant deities of Shiva]
-
A.
hasGuardianDeity
Indicates that an entity is under the protection or patronage of a specific guardian deity.
-
B.
hasDeities
chosen
Indicates that one entity possesses, is associated with, or is served by one or more deities.
-
C.
hasDeity
Indicates that one entity recognizes, worships, or is associated with another entity as its deity or divine figure.
-
D.
hasParentDeity
Indicates that one deity is the parent (progenitor or creator) of another deity.
-
E.
hasNumberOfDeities
Indicates the specific count of deities associated with an entity, such as a religion, mythology, or belief system.
- F. None of above.
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_69ef590ea74081908f0cd7500d85fa27 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f635a0a2788190bc17046fa79d26a6 |
completed | May 2, 2026, 5:34 p.m. |
| PD | Predicate disambiguation | batch_69f62c1a92648190835a2c5250d8c758 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:55 p.m.