Triple
T38462668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barelvi madrasas |
E912490
|
entity |
| Predicate | followsFiqh |
P160945
|
FINISHED |
| Object | Hanafi school of Islamic law |
—
|
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: Hanafi school of Islamic law | Statement: [Barelvi madrasas, followsFiqh, Hanafi school of Islamic law]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followsFiqh Context triple: [Barelvi madrasas, followsFiqh, Hanafi school of Islamic law]
-
A.
fiqh
Indicates the relationship of deriving, applying, or adhering to Islamic legal rulings and jurisprudential judgments regarding actions or situations.
-
B.
fiqhScope
Indicates the domain or scope within Islamic jurisprudence (fiqh) to which a particular ruling, issue, or concept applies.
-
C.
hasRulingInFiqh
Indicates that a subject has an associated legal ruling or judgment within the framework of Islamic jurisprudence (fiqh).
-
D.
majorFiqhText
Indicates that a work is recognized as a primary or foundational text within the field of Islamic jurisprudence (fiqh).
-
E.
الانتماء الفقهي
chosen
Indicates the doctrinal or jurisprudential school to which an entity is affiliated or adheres.
- 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_69f76e861d8c81908559031dc66e3c15 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ffac35ac5481908b6bdfd5bbe8c76e |
completed | May 9, 2026, 9:50 p.m. |
| PD | Predicate disambiguation | batch_69ffabbfd2548190964c851496bbbaee |
completed | May 9, 2026, 9:48 p.m. |
Created at: May 3, 2026, 4:31 p.m.