Triple
T22879323
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Codice dei beni culturali e del paesaggio |
E567415
|
entity |
| Predicate | definisce |
P773
|
FINISHED |
| Object | bene culturale |
—
|
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: bene culturale | Statement: [Codice dei beni culturali e del paesaggio, definisce, bene culturale]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: definisce Context triple: [Codice dei beni culturali e del paesaggio, definisce, bene culturale]
-
A.
defined
chosen
Indicates that one entity specifies, explains, or establishes the meaning, scope, or identity of another entity.
-
B.
definitionInvolves
Indicates that the meaning or explanation of one concept necessarily includes or depends on another concept.
-
C.
secondDefinition
Indicates that one entity serves as an alternative or secondary definition or meaning for another entity.
-
D.
definitionText
Indicates the textual content that provides the definition or explanatory meaning of a concept, term, or entity.
-
E.
wordDefinition
Indicates that one entity provides the meaning or explanation of a word represented by the other entity.
- 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_69e24589d8348190b96422d13a678bc1 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17f5b1ea481909a31a8ed6792ad04 |
completed | April 29, 2026, 3:47 a.m. |
| PD | Predicate disambiguation | batch_69ef3b6b2e2481908258156937b5a745 |
completed | April 27, 2026, 10:33 a.m. |
Created at: April 17, 2026, 3:39 p.m.