Triple
T14482758
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lance Armstrong |
E359151
|
entity |
| Predicate | tourDeFranceWinningYears |
P15810
|
FINISHED |
| Object | 1999 |
—
|
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: 1999 | Statement: [Lance Armstrong, tourDeFranceWinningYears, 1999]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tourDeFranceWinningYears Context triple: [Lance Armstrong, tourDeFranceWinningYears, 1999]
-
A.
TourDeFranceWins
Indicates the number of times an entity has won the Tour de France cycling race.
-
B.
firstTourDeFranceFinishYear
Indicates the year in which an entity (typically a cyclist) achieved their first finish in the Tour de France.
-
C.
TourDeFranceWin
chosen
Indicates that an entity has won the Tour de France cycling race, typically as the overall general classification winner for a given edition.
-
D.
TourDeFranceOverallWins
Indicates the number of times an entity has won the overall general classification of the Tour de France.
-
E.
GiroDItaliaOverallWinsYears
Indicates the specific years in which an entity achieved overall (general classification) victories in the Giro d'Italia.
- 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_69d8279740308190af9df93a3af8592e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de924bc548819087a2f693840d7426 |
completed | April 14, 2026, 7:15 p.m. |
| PD | Predicate disambiguation | batch_69de5c487b4c819097803e58dca628a5 |
completed | April 14, 2026, 3:24 p.m. |
Created at: April 10, 2026, 1:20 a.m.