Triple
T22334571
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salvi |
E552109
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object | Nicola Salvi |
—
|
NE NERFINISHED |
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: Nicola Salvi | Statement: [Salvi, hasNotableBearer, Nicola Salvi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nicola Salvi Context triple: [Salvi, hasNotableBearer, Nicola Salvi]
-
A.
Nicola Salvi
chosen
Nicola Salvi was an 18th-century Italian architect best known for designing Rome’s iconic Trevi Fountain.
-
B.
Domenico Fancelli
Domenico Fancelli was an Italian Renaissance sculptor renowned for his finely carved marble tombs and funerary monuments in Spain.
-
C.
Giacomo Quarenghi
Giacomo Quarenghi was an Italian neoclassical architect best known for his influential work at the Russian imperial court in Saint Petersburg.
-
D.
Giuseppe Valadier
Giuseppe Valadier was a prominent Italian neoclassical architect and urban planner of the late 18th and early 19th centuries, known for major restorations and redesigns in Rome.
-
E.
Bartolomeo Traballesi
Bartolomeo Traballesi was a 16th-century Italian Mannerist painter active in Florence, known for his contributions to Medici court commissions.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e482f788190b78d1588fc26d606 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1577e35f48190b11789d80182653e |
completed | April 29, 2026, 12:57 a.m. |
Created at: April 16, 2026, 8:43 p.m.