Triple
T25693033
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poigai Alvar |
E644247
|
entity |
| Predicate | hymnsCollectedIn |
P61726
|
FINISHED |
| Object | Nalayira Divya Prabandham |
—
|
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: Nalayira Divya Prabandham | Statement: [Poigai Alvar, hymnsCollectedIn, Nalayira Divya Prabandham]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hymnsCollectedIn Context triple: [Poigai Alvar, hymnsCollectedIn, Nalayira Divya Prabandham]
-
A.
hymnsPreservedIn
chosen
Indicates that specific hymns have been preserved or transmitted within a particular source, collection, or medium.
-
B.
hymnsDedicatedTo
Indicates that certain hymns are specifically devoted or addressed to a particular entity as their subject or object of veneration.
-
C.
associatedWithHymns
Indicates that something has a connection or relationship to hymns, such as being used in, derived from, or thematically linked to them.
-
D.
psalmCollection
Indicates that one entity is a collection or compilation that contains or groups together psalms associated with another entity.
-
E.
numberOfAttributedHymns
Indicates the quantity of hymns that are credited or assigned to a particular entity as their author or source.
- 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_69e77e82c9bc8190893090b2f6c64f1d |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f5fbc2bcbc81909e16230a8ed01210 |
completed | May 2, 2026, 1:27 p.m. |
| PD | Predicate disambiguation | batch_69f4807f8680819098a524158d049c63 |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 8:30 p.m.