Triple
T14082615
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arubathimoovar festival |
E338903
|
entity |
| Predicate | devoteePractices |
P68203
|
FINISHED |
| Object | singing devotional hymns |
—
|
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: singing devotional hymns | Statement: [Arubathimoovar festival, devoteePractices, singing devotional hymns]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: devoteePractices Context triple: [Arubathimoovar festival, devoteePractices, singing devotional hymns]
-
A.
devotionalPracticesInclude
chosen
Indicates that certain devotional practices form a part or subset of a broader set of devotional activities associated with an entity.
-
B.
templePractice
Indicates a religious or ritual activity that is performed within or in connection with a temple.
-
C.
devoteesSeek
Indicates that devoted followers actively seek out, pursue, or strive to approach the object of their devotion.
-
D.
practicesReligion
Indicates that an entity actively follows, observes, or participates in the beliefs, rituals, and customs of a particular religion.
-
E.
pilgrimagePractice
Indicates that an entity engages in, prescribes, or is associated with the religious act of undertaking a pilgrimage as a spiritual practice.
- 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_69d81c687b0c819087fd9ed4198403f8 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5ede40048190b465e909565730c1 |
completed | April 14, 2026, 3:35 p.m. |
| PD | Predicate disambiguation | batch_69de05b0e6c88190a819eeba0028981f |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:21 p.m.