Triple
T28979225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Martin |
E734498
|
entity |
| Predicate | vehicleTypeSpecialty |
P27118
|
FINISHED |
| Object | high-performance cars |
—
|
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: high-performance cars | Statement: [Frank Martin, vehicleTypeSpecialty, high-performance cars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vehicleTypeSpecialty Context triple: [Frank Martin, vehicleTypeSpecialty, high-performance cars]
-
A.
vehicleType
Indicates the specific kind or category of vehicle associated with an entity (e.g., car, bus, bicycle).
-
B.
vehicleTypeFocus
chosen
Indicates that the relationship or action specifically concerns or emphasizes a particular type or category of vehicle.
-
C.
vehicleClassServed
Indicates the class or type of vehicle that a service, facility, or operation is designed to accommodate or serve.
-
D.
vehicleEligibility
Indicates whether a given vehicle satisfies the required conditions or criteria to be considered eligible for a specified purpose or program.
-
E.
vehicleFamily
Indicates that two vehicles belong to the same family or category based on shared design, platform, or lineage.
- 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_69f05b0d1e7c819092baab93d3fe277e |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f65f7731e4819099d5bd3d915ee266 |
completed | May 2, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f65c2198208190a3954086c22cfcbf |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 9:10 a.m.