Triple
T11923906
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alpe d’Huez |
E283731
|
entity |
| Predicate | tourDeFranceStageType |
P47645
|
FINISHED |
| Object | mountain stage |
—
|
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: mountain stage | Statement: [Alpe d’Huez, tourDeFranceStageType, mountain stage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tourDeFranceStageType Context triple: [Alpe d’Huez, tourDeFranceStageType, mountain stage]
-
A.
timeTrialStages
Indicates that the related stages of a race are conducted as time trials, where participants compete individually against the clock rather than directly against each other.
-
B.
stageRaceType
chosen
Indicates the specific category or format of a multi-stage race within a broader competition or event.
-
C.
trekStage
Indicates a specific segment or leg within a longer trek or journey, typically ordered as part of a multi-stage route.
-
D.
GrandTour
Indicates a comprehensive, often extended journey or series of visits undertaken to explore multiple places, typically for cultural, educational, or experiential purposes.
-
E.
coreStageType
Indicates the specific kind or classification of a core stage within a larger process, system, or lifecycle.
- 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_69d6ab2ce9c48190b5d39511b524f666 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8e8e2fc648190a446c1917db1c7d9 |
completed | April 10, 2026, 12:11 p.m. |
| PD | Predicate disambiguation | batch_69d8bb3af0188190bfb22be5c97b3349 |
completed | April 10, 2026, 8:56 a.m. |
Created at: April 8, 2026, 9:45 p.m.