Triple
T7699014
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rosa Vercellana |
E174441
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Rosa Vercellana |
E174441
|
NE 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: Rosa Vercellana | Statement: [Rosa Vercellana, name, Rosa Vercellana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rosa Vercellana Context triple: [Rosa Vercellana, name, Rosa Vercellana]
-
A.
Rosa Vercellana
chosen
Rosa Vercellana was the morganatic wife of King Victor Emmanuel II of Italy, noted for her rise from commoner to countess and her controversial position at the Savoy court.
-
B.
Rosa Maltoni
Rosa Maltoni was an Italian schoolteacher best known as the wife of Alessandro Mussolini and the mother of Benito Mussolini.
-
C.
Manuela Testolini
Manuela Testolini is a Canadian businesswoman and philanthropist, known for founding the nonprofit In a Perfect World and for her previous marriage to musician Prince.
-
D.
Maria Ricossa
Maria Ricossa is a Canadian actress known for her work in film, television, and theatre.
-
E.
Ylenia Carrisi
Ylenia Carrisi is the missing daughter of Italian singer and actor Al Bano and American actress Romina Power, whose mysterious disappearance in 1994 drew widespread media attention.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c6995a72cc8190998e56daa6f8e453 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7026a8268819097c03458ed263a55 |
completed | March 27, 2026, 10:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8e57c9e00819096730c74c5202027 |
completed | March 29, 2026, 8:40 a.m. |
Created at: March 27, 2026, 4:03 p.m.