Triple
T8493574
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | submarine Proteus |
E201035
|
entity |
| Predicate | visualDesignFeature |
P29429
|
FINISHED |
| Object | sleek white hull |
—
|
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: sleek white hull | Statement: [submarine Proteus, visualDesignFeature, sleek white hull]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: visualDesignFeature Context triple: [submarine Proteus, visualDesignFeature, sleek white hull]
-
A.
designedFeature
Indicates that one entity is a feature or component intentionally planned, created, or specified by another entity as part of a design.
-
B.
visualElements
chosen
Indicates that one entity contains, uses, or is characterized by specific visual components or graphical features associated with another entity.
-
C.
previousDesignFeature
Indicates that one design feature precedes another in a sequence or earlier version of a design.
-
D.
visualSimplicity
Indicates that something is characterized by a minimal, uncluttered, and easy-to-perceive visual appearance or design.
-
E.
designEmphasizes
Indicates that a design intentionally places special importance or focus on a particular feature, principle, or aspect over others.
- 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_69ca831ee390819095fae73400bbfafc |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe579b7088190b297b04527e36a2b |
completed | March 31, 2026, 3:17 p.m. |
| PD | Predicate disambiguation | batch_69cbd10a4b0881909e254117780dc823 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:13 p.m.