Triple
T22334575
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nicola Salvi |
E552109
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | 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: Salvi | Statement: [Nicola Salvi, familyName, Salvi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Salvi Context triple: [Nicola Salvi, familyName, Salvi]
-
A.
Salvi
chosen
Salvi is an Italian surname most notably associated with Nicola Salvi, the 18th-century architect of Rome’s Trevi Fountain.
-
B.
Salvati
Salvati is an Italian surname associated with figures such as Scipione Salvati Borghese and other members of Italian noble or notable families.
-
C.
Rainaldi
Rainaldi is an Italian surname most notably associated with the Baroque architect Girolamo Rainaldi and his family of artists and architects.
-
D.
Leonforte
Leonforte is a town and comune in central Sicily, Italy, known for its historic architecture and agricultural traditions within the Province of Enna.
-
E.
Mastroeni
Mastroeni is the surname of Pablo Mastroeni, a former professional soccer player and coach best known for his career with the U.S. national team and Major League Soccer.
- 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.