Triple
T20157732
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Valide Sultan |
E491616
|
entity |
| Predicate | patronageForm |
P56144
|
FINISHED |
| Object | construction of mosques |
—
|
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: construction of mosques | Statement: [Valide Sultan, patronageForm, construction of mosques]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: patronageForm Context triple: [Valide Sultan, patronageForm, construction of mosques]
-
A.
patronage
Indicates a relationship where one party supports, sponsors, or protects another, often in exchange for loyalty, services, or influence.
-
B.
patronageFrom
Indicates a relationship where support, sponsorship, or backing is provided to someone or something by a patron.
-
C.
patronageFocus
chosen
Indicates the primary area, subject, or domain that is the focus of an entity’s support, sponsorship, or patronage.
-
D.
patronageStyle
Indicates the manner or characteristic way in which support, sponsorship, or patronage is provided in a relationship.
-
E.
patronageHouse
Indicates a relationship in which one entity serves as the patron or sponsoring house of another, providing support, backing, or protection.
- 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_69da6265f8f0819080b29c752a574088 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e667e18a0c8190a2cc2b305da28047 |
completed | April 20, 2026, 5:52 p.m. |
| PD | Predicate disambiguation | batch_69e54cfd924881909b55f3e4d3e7e070 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 11:34 p.m.