Triple
T27889694
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Upper Basilica |
E705318
|
entity |
| Predicate | frescoSubject |
P23612
|
FINISHED |
| Object | scenes from the life of Saint Francis |
—
|
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: scenes from the life of Saint Francis | Statement: [Upper Basilica, frescoSubject, scenes from the life of Saint Francis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frescoSubject Context triple: [Upper Basilica, frescoSubject, scenes from the life of Saint Francis]
-
A.
hasFrescoBy
Indicates that something (typically a building, room, or wall) contains or features a fresco created by a specified artist.
-
B.
frescoCycleBy
Indicates that one fresco belongs to, or is part of, a larger thematic or narrative cycle of frescoes.
-
C.
hasFrescoes
chosen
Indicates that something contains or is adorned with fresco paintings as part of its structure or decoration.
-
D.
frescoesDate
Indicates that a fresco is associated with a specific date or time period of its creation or execution.
-
E.
frescoExecutionEnd
Indicates the point in time or event at which the execution or performance of a fresco-related process or action comes to an end.
- 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_69ef96b39c448190a9b3aa6672a5168f |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f639b3f8608190a96e104003ca3990 |
completed | May 2, 2026, 5:51 p.m. |
| PD | Predicate disambiguation | batch_69f6318be69481909d1bcf29b7b60eb2 |
completed | May 2, 2026, 5:17 p.m. |
Created at: April 27, 2026, 6:35 p.m.