Triple
T2956701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Citroën Ami |
E79947
|
entity |
| Predicate | doorDesign |
P8655
|
FINISHED |
| Object | symmetrical doors with opposite opening directions |
—
|
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: symmetrical doors with opposite opening directions | Statement: [Citroën Ami, doorDesign, symmetrical doors with opposite opening directions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: doorDesign Context triple: [Citroën Ami, doorDesign, symmetrical doors with opposite opening directions]
-
A.
doorType
chosen
Indicates the specific kind or category of door associated with an entity.
-
B.
wallFeature
Indicates that one entity functions as a structural or design feature associated with a wall of another entity.
-
C.
interiorStyle
Indicates that one entity has a particular interior design style or aesthetic characterized by the other entity.
-
D.
furnishingType
Indicates the type or category of furnishings associated with an entity, such as a property or room.
-
E.
doorAndWindowDetail
Indicates a relationship that specifies detailed characteristics or features shared by both doors and windows.
- 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_69ad8b1276588190a374a0b12e0f7bdf |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad992998f08190ac9428310983172e |
completed | March 8, 2026, 3:43 p.m. |
| PD | Predicate disambiguation | batch_69ad960c5c8881909d679912bd7d78f3 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:57 p.m.