Triple
T20355817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Italo De Zan |
E496642
|
entity |
| Predicate | GiroStageWinYear |
P118624
|
FINISHED |
| Object | 1948 |
—
|
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: 1948 | Statement: [Italo De Zan, GiroStageWinYear, 1948]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: GiroStageWinYear Context triple: [Italo De Zan, GiroStageWinYear, 1948]
-
A.
GiroDItaliaOverallWinsYears
Indicates the specific years in which an entity achieved overall (general classification) victories in the Giro d'Italia.
-
B.
grandTourStageWin
chosen
Indicates that an individual has won a stage in one of cycling’s Grand Tours (Tour de France, Giro d’Italia, or Vuelta a España).
-
C.
TourDeFranceWins
Indicates the number of times an entity has won the Tour de France cycling race.
-
D.
numberOfTourDeFranceStageWins
Indicates the total count of Tour de France stages that an entity (typically a cyclist) has won.
-
E.
TourDeFranceWin
Indicates that an entity has won the Tour de France cycling race, typically as the overall general classification winner for a given edition.
- 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_69e0b4a3f7f48190b37f354574028ca6 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67853f10881908ecde94036804a8a |
completed | April 20, 2026, 7:02 p.m. |
| PD | Predicate disambiguation | batch_69e57636b4808190bc2855af48a3ccdc |
completed | April 20, 2026, 12:41 a.m. |
Created at: April 16, 2026, 11:25 a.m.