Triple
T23912830
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vanwall |
E601990
|
entity |
| Predicate | aerodynamicist |
P69420
|
FINISHED |
| Object | Frank Costin |
—
|
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: Frank Costin | Statement: [Vanwall, aerodynamicist, Frank Costin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aerodynamicist Context triple: [Vanwall, aerodynamicist, Frank Costin]
-
A.
aerodynamicsDeveloper
chosen
Indicates that an entity (typically a person or organization) is responsible for designing, developing, or improving the aerodynamic properties of another entity.
-
B.
airframeDesigner
Indicates that one entity is the designer or design authority responsible for the airframe of an aircraft or aerospace vehicle associated with the other entity.
-
C.
aerodynamicsFeature
Indicates that one entity possesses or is characterized by a specific aerodynamic property, component, or design feature affecting airflow and motion through air.
-
D.
aerodynamicGoal
Indicates a goal or objective specifically related to aerodynamic performance, behavior, or properties in a given context.
-
E.
architectOfWing
Indicates that one entity served as the architect responsible for designing a particular wing of a building or structure.
- 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_69f1ce96c47881908ccb17ef9f750676 |
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, 8:39 p.m.