Triple
T27623095
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Umm al-Fadl bint al-Ma'mun |
E696129
|
entity |
| Predicate | associatedImam |
P35869
|
FINISHED |
| Object | Muhammad al-Jawad |
—
|
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: Muhammad al-Jawad | Statement: [Umm al-Fadl bint al-Ma'mun, associatedImam, Muhammad al-Jawad]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedImam Context triple: [Umm al-Fadl bint al-Ma'mun, associatedImam, Muhammad al-Jawad]
-
A.
associatedWithImamNumber
Indicates a relationship where an entity is linked to, or identified by, a specific numbered Imam in a sequence of Imams.
-
B.
hasImam
chosen
Indicates that an entity is associated with, led by, or served by a particular imam in a religious or community context.
-
C.
regardedAsImamBy
Indicates that one entity is considered or recognized as an imam (religious leader) by another entity.
-
D.
guardianOrImam
Indicates a relationship where one entity serves as a guardian or religious leader (imam) responsible for the care, guidance, or representation of another entity.
-
E.
numberOfImams
Indicates the count of distinct imams associated with or relevant to a given entity or context.
- 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_69ef59092c8881908114ad184248cc46 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_6a0027e4a59481909417b2531daaf480 |
completed | May 10, 2026, 6:38 a.m. |
| PD | Predicate disambiguation | batch_6a0026a42bc08190ad3322ce625a523a |
completed | May 10, 2026, 6:33 a.m. |
Created at: April 27, 2026, 2:16 p.m.