Triple
T23911332
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Debbie Dunham |
E601945
|
entity |
| Predicate | ridesIn |
P23429
|
FINISHED |
| Object | 1958 Chevrolet Impala |
—
|
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: 1958 Chevrolet Impala | Statement: [Debbie Dunham, ridesIn, 1958 Chevrolet Impala]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ridesIn Context triple: [Debbie Dunham, ridesIn, 1958 Chevrolet Impala]
-
A.
ridesWith
Indicates that one entity is traveling together in the same vehicle or conveyance as another entity.
-
B.
rides
chosen
Indicates that one entity travels on or is carried by another entity as a passenger or operator.
-
C.
isRiddenBy
Indicates that an entity serves as a mount or vehicle that is being ridden by another entity.
-
D.
transportIncludes
Indicates that a broader transport operation or service encompasses, contains, or makes use of a specific transport segment, mode, or component as part of its overall movement.
-
E.
hasRidingAssociation
Indicates an association where one entity is related to another through the act or context of riding (e.g., serving as rider, mount, or riding partner).
- 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_69e2953a187081908346a9f36e85fc98 |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1ce94f65c8190807723344fa0b837 |
completed | April 29, 2026, 9:25 a.m. |
| PD | Predicate disambiguation | batch_69f16151ebdc819086e9e1d7cc1f4f3c |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:38 p.m.