Triple
T16645273
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poggio di Sanremo |
E404450
|
entity |
| Predicate | typicalRacePosition |
P112307
|
FINISHED |
| Object | near the finish of Milan–San Remo |
—
|
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: near the finish of Milan–San Remo | Statement: [Poggio di Sanremo, typicalRacePosition, near the finish of Milan–San Remo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalRacePosition Context triple: [Poggio di Sanremo, typicalRacePosition, near the finish of Milan–San Remo]
-
A.
positionOnRace
Indicates the relative ranking or placement an entity holds within the context of a race or competitive event.
-
B.
bestRaceFinishPositionAchievedByDriver
Indicates the best (highest-ranking) race finishing position that a particular driver has ever achieved.
-
C.
typicalPositionType
chosen
Indicates the usual or most common positional role or placement type that an entity generally occupies or is associated with.
-
D.
polePositions
Indicates that one entity holds the pole position (starting first) relative to another entity in a competitive event, such as a race.
-
E.
polePositionDriverNationality
Indicates the nationality associated with the driver who secured pole position in a race.
- 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_69d8838a41f08190b0c3f79c47df5078 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37ad4735c81908a3a227bf02ca489 |
completed | April 18, 2026, 12:36 p.m. |
| PD | Predicate disambiguation | batch_69e296af2f88819092c9ffee4a65d7dd |
completed | April 17, 2026, 8:23 p.m. |
Created at: April 10, 2026, 5:18 a.m.