Triple
T26461935
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brendon Hartley |
E665660
|
entity |
| Predicate | testDriverFor |
P160775
|
FINISHED |
| Object | Scuderia Toro Rosso |
—
|
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: Scuderia Toro Rosso | Statement: [Brendon Hartley, testDriverFor, Scuderia Toro Rosso]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: testDriverFor Context triple: [Brendon Hartley, testDriverFor, Scuderia Toro Rosso]
-
A.
testDriverFor
chosen
Indicates that one entity serves as a test driver (a controlling or invoking component) for exercising or validating another entity.
-
B.
driverFor
Indicates that one entity serves as the driver or operator of a vehicle or transport service for another entity.
-
C.
testRiderFor
Indicates that a rider is being evaluated, examined, or assessed for a particular purpose, condition, or qualification.
-
D.
driverType
Indicates the category or role of a driver associated with an entity or activity (e.g., primary, backup, commercial, etc.).
-
E.
hasDriver
Indicates that an entity is operated, controlled, or driven by a specific person or agent.
- 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_69ee883e812c8190a9b5a9cdb87fee5e |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f612956424819083b0e451342a5811 |
completed | May 2, 2026, 3:04 p.m. |
| PD | Predicate disambiguation | batch_69f60b89cc048190a9feb24466006be0 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 27, 2026, 12:13 a.m.