Triple
T25340997
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Senna–Prost collision 1990 practice crash |
E635411
|
entity |
| Predicate | involvedDriver |
P103677
|
FINISHED |
| Object | Ayrton Senna |
—
|
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: Ayrton Senna | Statement: [Senna–Prost collision 1990 practice crash, involvedDriver, Ayrton Senna]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: involvedDriver Context triple: [Senna–Prost collision 1990 practice crash, involvedDriver, Ayrton Senna]
-
A.
alsoAssociatedWithDriver
Indicates that an entity has an additional or secondary association with a specified driver, beyond any primary or previously stated driver relationship.
-
B.
associatedWithDriver
chosen
Indicates that one entity has a connection or relationship with a specific driver, such as being linked, assigned, or otherwise related to that driver.
-
C.
utilityInvolved
Indicates that a utility service or provider is involved in, associated with, or plays a role in the referenced situation or relationship.
-
D.
drivers
Indicates that one entity operates or controls a vehicle or means of transport for another entity or in a given context.
-
E.
isDriven
Indicates that one entity operates or controls the movement of another entity, typically a vehicle or device.
- 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_69e75a99bd6481909476115b35b9a8e4 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f661b58ac48190907b6c6e9ccc2c59 |
completed | May 2, 2026, 8:42 p.m. |
| PD | Predicate disambiguation | batch_69f660eea4648190b0d5e24293607813 |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 21, 2026, 1:32 p.m.