Triple
T24564249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jordan Grand Prix |
E607739
|
entity |
| Predicate | 1999LeadDriver |
P42641
|
FINISHED |
| Object | Heinz-Harald Frentzen |
—
|
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: Heinz-Harald Frentzen | Statement: [Jordan Grand Prix, 1999LeadDriver, Heinz-Harald Frentzen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 1999LeadDriver Context triple: [Jordan Grand Prix, 1999LeadDriver, Heinz-Harald Frentzen]
-
A.
bestDriver
Indicates that the subject is considered the most skilled or highest-performing driver within a specified group or context.
-
B.
notableFormerDriver
chosen
Indicates that a person was previously a prominent or distinguished driver for the referenced entity (such as a team, organization, or company).
-
C.
featuresDrivers
Indicates that something includes or highlights specific drivers as notable components or participants.
-
D.
debutDriver
Indicates the driver who made their first official appearance or start in a particular event, season, or competition.
-
E.
possibleDriver
Indicates that an entity is a candidate or potential driver of another entity, such as a possible cause, regulator, or influencing factor.
- 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_69e2c4cc35a48190990b7571bc086df8 |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2a8f9d0f881909afc04537c32f76b |
completed | April 30, 2026, 12:57 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b99e7c8190ba7e2dc8729a314a |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:28 a.m.