Triple
T4341290
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barberini |
E97784
|
entity |
| Predicate | patronageFocus |
P56144
|
FINISHED |
| Object | church decoration in Rome |
—
|
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: church decoration in Rome | Statement: [Barberini, patronageFocus, church decoration in Rome]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: patronageFocus Context triple: [Barberini, patronageFocus, church decoration in Rome]
-
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.
patronageStyle
Indicates the manner or characteristic way in which support, sponsorship, or patronage is provided in a relationship.
-
D.
patronageArea
Indicates the geographic or administrative area within which a patron (such as a sponsor, supporter, or benefactor) exercises their support, influence, or protective role.
-
E.
hasPatronageOver
Indicates that one entity serves as a patron, sponsor, or protector for another, exercising support, guidance, or authority over it.
- F. None of above. chosen
Provenance (4 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_69b34548402c819085ab68b27c235a87 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35170a6648190a15ffb21640ee478 |
completed | March 12, 2026, 11:51 p.m. |
| PD | Predicate disambiguation | batch_69b34f4fe1c481908d6d66e15697c04b |
completed | March 12, 2026, 11:42 p.m. |
| PDg | Predicate description generation | batch_69b350d1649881908fa6556d875a8b4d |
completed | March 12, 2026, 11:48 p.m. |
Created at: March 12, 2026, 11:14 p.m.