Triple
T36946835
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yawm al-Jumu'ah |
E913935
|
entity |
| Predicate | sermonLanguageTradition |
P87892
|
FINISHED |
| Object | often Arabic in many regions |
—
|
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: often Arabic in many regions | Statement: [Yawm al-Jumu'ah, sermonLanguageTradition, often Arabic in many regions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sermonLanguageTradition Context triple: [Yawm al-Jumu'ah, sermonLanguageTradition, often Arabic in many regions]
-
A.
languageOfSermon
chosen
Indicates the language in which a sermon is delivered or composed.
-
B.
sermonBy
Indicates that a sermon is delivered, authored, or given by a particular person or agent.
-
C.
languageOfGospelTraditionally
Indicates the language in which a particular Gospel is traditionally believed or held to have been written or transmitted.
-
D.
worshipTradition
Indicates that one entity follows, practices, or is associated with a particular religious or spiritual worship tradition.
-
E.
liturgicalTradition
Indicates the specific religious rite or ceremonial tradition according to which a worship service, practice, or community operates.
- 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_69f76e8b28848190abd81fe7a7374910 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fa0a7b00948190a257273d9968c5d7 |
completed | May 5, 2026, 3:19 p.m. |
| PD | Predicate disambiguation | batch_69f9fec9c9488190ae2a349651a02782 |
completed | May 5, 2026, 2:29 p.m. |
Created at: May 3, 2026, 4:13 p.m.