Triple
T15842897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adrian Sutil |
E384139
|
entity |
| Predicate | kartingBackground |
P120089
|
FINISHED |
| Object | started racing in karting before moving to single-seaters |
—
|
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: started racing in karting before moving to single-seaters | Statement: [Adrian Sutil, kartingBackground, started racing in karting before moving to single-seaters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: kartingBackground Context triple: [Adrian Sutil, kartingBackground, started racing in karting before moving to single-seaters]
-
A.
hasKartingTrack
Indicates that one entity possesses or includes a karting track as a facility or feature.
-
B.
styleOfRacing
Indicates the specific manner or approach in which an entity participates in or performs racing.
-
C.
hasMotorRacingCircuit
Indicates that a location or entity possesses, contains, or is the site of a motor racing circuit.
-
D.
raceComponent
Indicates that one entity is a constituent part, segment, or stage within a larger race or racing event involving another entity.
-
E.
racingDivision
Indicates that one entity is classified into, or associated with, a particular racing division within a competitive racing context.
- F. None of above. chosen
Provenance (4 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_69d86da34c888190976e06c4019d415a |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e142ea3da08190a9d2d5917f84907c |
completed | April 16, 2026, 8:13 p.m. |
| PD | Predicate disambiguation | batch_69e005434ed88190baf11c169da3cf29 |
completed | April 15, 2026, 9:38 p.m. |
| PDg | Predicate description generation | batch_69e007869ae481909473ee220a7ccdb5 |
completed | April 15, 2026, 9:47 p.m. |
Created at: April 10, 2026, 4:50 a.m.