Triple
T6517906
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salah in Islam |
E148309
|
entity |
| Predicate | specialOccasionPrayer |
P61722
|
FINISHED |
| Object | Eid prayer |
—
|
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: Eid prayer | Statement: [Salah in Islam, specialOccasionPrayer, Eid prayer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: specialOccasionPrayer Context triple: [Salah in Islam, specialOccasionPrayer, Eid prayer]
-
A.
associatedPrayer
Indicates a relationship where a specific prayer is linked or connected to another entity, such as an event, object, person, or religious context.
-
B.
prayerIntention
Indicates that one entity directs a prayer or spiritual request specifically on behalf of, or concerning, another entity or situation.
-
C.
specialOccasion
chosen
Indicates that an event or situation is associated with a notable or exceptional occasion, such as a celebration, milestone, or culturally significant date.
-
D.
prayerCall
Indicates that one entity issues or performs a call to prayer directed toward others.
-
E.
praysBefore
Indicates that one entity performs an act of prayer earlier in time than another entity or event.
- 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_69c687e68e748190baceb9298f32d3ed |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6ac108abc819082d1368af6611a92 |
completed | March 27, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69c68ab98c78819081743e614df04e1d |
completed | March 27, 2026, 1:48 p.m. |
Created at: March 27, 2026, 1:44 p.m.