Triple
T31030629
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vélodrome André-Pétrieux |
E790710
|
entity |
| Predicate | hasFinishLineFor |
P113802
|
FINISHED |
| Object | Paris–Roubaix men’s race |
—
|
NE NERFINISHED |
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: Paris–Roubaix men’s race | Statement: [Vélodrome André-Pétrieux, hasFinishLineFor, Paris–Roubaix men’s race]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFinishLineFor Context triple: [Vélodrome André-Pétrieux, hasFinishLineFor, Paris–Roubaix men’s race]
-
A.
isFinishLineOf
chosen
Indicates that something serves as the finish line or endpoint for a particular event, race, or process.
-
B.
hasSprintFinish
Indicates that an event, activity, or process concludes with a short, intense final effort or burst of speed.
-
C.
isOfficialFinishFor
Indicates that one event, result, or record serves as the formally recognized completion point for another process, activity, or competition.
-
D.
hasTypicalFinish
Indicates that one entity characteristically or commonly concludes, completes, or ends with another entity.
-
E.
hasStartFinishStraight
Indicates that something includes a straight segment that serves as both the starting and finishing section of a course or track.
- 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_69f224c97a788190b5da1ead6038a74e |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fe59d11e9881909d2f33b7c717030e |
completed | May 8, 2026, 9:46 p.m. |
| PD | Predicate disambiguation | batch_69fe394fdfbc8190a931926ae3635cbf |
completed | May 8, 2026, 7:28 p.m. |
Created at: April 29, 2026, 8:59 p.m.