Triple
T34368864
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Thorndyke |
E882096
|
entity |
| Predicate | usesVehicleBrand |
P19188
|
FINISHED |
| Object | Thorndyke Special |
—
|
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: Thorndyke Special | Statement: [Peter Thorndyke, usesVehicleBrand, Thorndyke Special]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesVehicleBrand Context triple: [Peter Thorndyke, usesVehicleBrand, Thorndyke Special]
-
A.
usesVehicleVariant
Indicates that one entity performs an action or function by employing a specific variant or version of a vehicle.
-
B.
vehicleUsed
Indicates that a particular vehicle is utilized or employed in performing an action, event, or activity.
-
C.
usesTransportBrand
chosen
Indicates that one entity makes use of a transportation service, vehicle, or system associated with a specific brand.
-
D.
usedByVehicleType
Indicates that something (such as a resource, component, or facility) is utilized or operated by a specific type or category of vehicle.
-
E.
hasVehicularUse
Indicates that something is used for, intended for, or associated with operation by vehicles or vehicular traffic.
- 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_69f349be5c9c81908dc726ae1f4c68f2 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71c35327c8190884f1bfe12bd2cd7 |
completed | May 3, 2026, 9:58 a.m. |
| PD | Predicate disambiguation | batch_69f71822d0e88190ac9731c7ae5a4def |
completed | May 3, 2026, 9:40 a.m. |
Created at: May 1, 2026, 1:58 a.m.