Triple
T10933494
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manghit dynasty |
E258267
|
entity |
| Predicate | religiousInstitutionSupported |
P20650
|
FINISHED |
| Object | madrasas |
—
|
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: madrasas | Statement: [Manghit dynasty, religiousInstitutionSupported, madrasas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: religiousInstitutionSupported Context triple: [Manghit dynasty, religiousInstitutionSupported, madrasas]
-
A.
religiousFoundation
Indicates that an entity was established, created, or founded by a religious organization, authority, or tradition.
-
B.
religiousAccreditation
Indicates that an entity has been formally recognized or certified by a religious authority or organization as meeting specified religious standards or criteria.
-
C.
hasReligiousInstitutionType
Indicates that an entity is associated with, or classified by, a specific type of religious institution.
-
D.
hasReligiousSponsor
chosen
Indicates that an entity is financially or organizationally supported by a religious individual, group, or institution.
-
E.
hasReligiousOrganization
Indicates that an entity is associated with, governed by, or belongs to a specific religious organization.
- 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_69d6aa8769b4819082bfe5e61b9017f0 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d770ae073881909720febe9f5f296a |
completed | April 9, 2026, 9:26 a.m. |
| PD | Predicate disambiguation | batch_69d72e799f808190b6ab64fc7586a303 |
completed | April 9, 2026, 4:43 a.m. |
Created at: April 8, 2026, 9:23 p.m.