Triple
T3663622
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris–Roubaix |
E77707
|
entity |
| Predicate | typeOfFinish |
P47075
|
FINISHED |
| Object | velodrome finish |
—
|
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: velodrome finish | Statement: [Paris–Roubaix, typeOfFinish, velodrome finish]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfFinish Context triple: [Paris–Roubaix, typeOfFinish, velodrome finish]
-
A.
typicalFinish
Indicates that an action, process, or event commonly or characteristically ends with a particular outcome or state.
-
B.
finishingArea
chosen
Indicates the location or area where an activity, process, or event comes to an end or is completed.
-
C.
furnishingType
Indicates the type or category of furnishings associated with an entity, such as a property or room.
-
D.
materialUsed
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
-
E.
typeOfFixing
Indicates the specific method or manner in which one entity is fastened, attached, or secured to another.
- 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_69ad85dfc4dc8190a441864202ab2a7a |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc3fe5eb08190ab15044acf9ac8a9 |
completed | March 8, 2026, 6:46 p.m. |
| PD | Predicate disambiguation | batch_69adb847e9d881909dad2ffd0f3b6c15 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:25 p.m.