Triple
T16883928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herman Van Springel |
E421489
|
entity |
| Predicate | GrandTourResult |
P84829
|
FINISHED |
| Object | 2nd overall Tour de France 1968 |
—
|
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: 2nd overall Tour de France 1968 | Statement: [Herman Van Springel, GrandTourResult, 2nd overall Tour de France 1968]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: GrandTourResult Context triple: [Herman Van Springel, GrandTourResult, 2nd overall Tour de France 1968]
-
A.
GrandTour
Indicates a comprehensive, often extended journey or series of visits undertaken to explore multiple places, typically for cultural, educational, or experiential purposes.
-
B.
bestTourDeFranceResult
Indicates the highest (best) finishing position an entity has ever achieved in the Tour de France.
-
C.
TourDeFranceOverallWins
Indicates the number of times an entity has won the overall general classification of the Tour de France.
-
D.
grandTourPodium
chosen
Indicates that an entity achieved a top-three overall finish in a Grand Tour cycling race.
-
E.
grandTourStageWin
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).
- 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_69d889d470fc8190b4aec199636c0c56 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e3bbbf0cec819084216807601afad1 |
completed | April 18, 2026, 5:13 p.m. |
| PD | Predicate disambiguation | batch_69e32b90ec3c819099c51bb7baf2984c |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:29 a.m.