Triple
T21391992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Luigi Ganna |
E527676
|
entity |
| Predicate | won |
P1518
|
FINISHED |
| Object | Milano–Sanremo |
—
|
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: Milano–Sanremo | Statement: [Luigi Ganna, won, Milano–Sanremo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Milano–Sanremo Context triple: [Luigi Ganna, won, Milano–Sanremo]
-
A.
Milan–San Remo
chosen
Milan–San Remo is one of cycling’s oldest and most prestigious one-day “Monument” classics, renowned for its exceptionally long distance and sprinter-friendly route from Milan to the Italian Riviera.
-
B.
Le Lombard
Le Lombard is a Belgian comic book publisher renowned for releasing many classic Franco-Belgian series.
-
C.
Giro di Lombardia
Giro di Lombardia is a prestigious late-season one-day professional cycling classic in Italy, renowned for its hilly course and status as one of the sport’s five Monuments.
-
D.
Giro del Veneto
The Giro del Veneto is a historic professional one-day road cycling race held in the Veneto region of Italy.
-
E.
Paris–Nice
Paris–Nice is a prestigious early-season professional road cycling stage race in France, often seen as a key preparation event for the Grand Tours.
- 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_69e0b51ff3748190935c0a513c62a12b |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69ee62cbfef08190a33ac1f198c82cd0 |
completed | April 26, 2026, 7:09 p.m. |
Created at: April 16, 2026, 5:13 p.m.