Triple
T27015746
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bernd Rosemeyer |
E680522
|
entity |
| Predicate | vehicleUsedAtDeath |
P59942
|
FINISHED |
| Object | Auto Union streamliner |
—
|
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: Auto Union streamliner | Statement: [Bernd Rosemeyer, vehicleUsedAtDeath, Auto Union streamliner]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vehicleUsedAtDeath Context triple: [Bernd Rosemeyer, vehicleUsedAtDeath, Auto Union streamliner]
-
A.
vehicleUsed
Indicates that a particular vehicle is utilized or employed in performing an action, event, or activity.
-
B.
modeOfTransportAtDeath
chosen
Indicates the means or vehicle by which a person was traveling at the time of their death.
-
C.
usedAsVehicleFor
Indicates that one entity functions as a means of transportation or conveyance for another entity.
-
D.
driverOfVictimVehicle
Indicates that an entity is the person who was driving the vehicle occupied or owned by the victim at the time of the relevant incident.
-
E.
vehicleFor
Indicates that one entity serves as the means of transportation or conveyance for another entity.
- 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_69eeeb5450988190bfc9a3c012ac463a |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f625411c14819086492062e86ba8d5 |
completed | May 2, 2026, 4:24 p.m. |
| PD | Predicate disambiguation | batch_69f623a91b9c8190b2e2fdbc55cb89b6 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 7:06 a.m.