Triple
T5248402
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Appar |
E118518
|
entity |
| Predicate | hymnsAddress |
P60491
|
FINISHED |
| Object | various Shiva temples across Tamil Nadu |
—
|
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 Shiva temples across Tamil Nadu | Statement: [Appar, hymnsAddress, various Shiva temples across Tamil Nadu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hymnsAddress Context triple: [Appar, hymnsAddress, various Shiva temples across Tamil Nadu]
-
A.
associatedWithHymns
chosen
Indicates that something has a connection or relationship to hymns, such as being used in, derived from, or thematically linked to them.
-
B.
hymnNumber
Indicates the specific numerical designation assigned to a hymn within a hymnal or song collection.
-
C.
importantHymn
Indicates that a hymn holds significant importance or prominence within a particular religious, cultural, or musical context.
-
D.
isAddressedInPrayer
Indicates that an entity is the recipient or target of a prayer being spoken or offered.
-
E.
isAnthemFor
Indicates that a song or musical composition serves as the official anthem representing a particular group, organization, place, or cause.
- 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_69bd4468aacc8190a8196f71855cdf4f |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7b77165c8190bd1ce8a197cef226 |
completed | March 20, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69bd77c30bac8190a883ca45da35d667 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:50 p.m.