Triple
T35751849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Giuseppe Farina |
E1033338
|
entity |
| Predicate | droveForConstructor |
P72458
|
FINISHED |
| Object | Alfa Romeo |
—
|
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: Alfa Romeo | Statement: [Giuseppe Farina, droveForConstructor, Alfa Romeo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: droveForConstructor Context triple: [Giuseppe Farina, droveForConstructor, Alfa Romeo]
-
A.
racedForConstructor
chosen
Indicates that an entity competed as a driver on behalf of a particular constructor (team) in a race or racing season.
-
B.
droveFor
Indicates that one entity operated a vehicle on behalf of, or in service to, another entity for a certain period or purpose.
-
C.
drivenFrom
Indicates that one entity has been forced or compelled to leave or move away from another entity or location.
-
D.
producedDriver
Indicates that an entity (such as a manufacturer or organization) created or brought into existence a particular driver (such as a software or hardware driver).
-
E.
drivenTo
Indicates that one entity causes or compels another entity to move or act toward a particular state, goal, or location.
- 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_69f76e1262f48190a313318665acc189 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7a197aee48190bbd69f670a3f7721 |
completed | May 3, 2026, 7:27 p.m. |
| PD | Predicate disambiguation | batch_69f7a070e23881909a233370acb57384 |
completed | May 3, 2026, 7:22 p.m. |
Created at: May 3, 2026, 4:06 p.m.