Triple
T37349586
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mushaf al-Madina |
E927284
|
entity |
| Predicate | recitationReference |
P9184
|
FINISHED |
| Object | Hafs ‘an ‘Asim |
—
|
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: Hafs ‘an ‘Asim | Statement: [Mushaf al-Madina, recitationReference, Hafs ‘an ‘Asim]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recitationReference Context triple: [Mushaf al-Madina, recitationReference, Hafs ‘an ‘Asim]
-
A.
recitationObject
Indicates that something is the content or material being recited in a recitation event.
-
B.
recitationConsidered
Indicates that one entity regards or evaluates a particular recitation (such as a spoken or performed rendering of content) in a certain way or with a certain status.
-
C.
recitationTradition
chosen
Indicates a relationship where a text, work, or content is transmitted or performed according to a particular established style, method, or lineage of recitation.
-
D.
recitationRecommended
Indicates that a particular recitation session or section is recommended for an entity, such as a student or course.
-
E.
recitationRecommendedBy
Indicates that one entity recommends or endorses another entity as suitable or preferred for recitation.
- 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_69f76eb5e034819088e53ab5b7909a68 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb8c38a9688190be524246f5682107 |
completed | May 6, 2026, 6:45 p.m. |
| PD | Predicate disambiguation | batch_69fb5a9c6e0481908565bd849e869b24 |
completed | May 6, 2026, 3:13 p.m. |
Created at: May 3, 2026, 4:16 p.m.