Triple
T12047409
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | iPad Air (4th generation) |
E286821
|
entity |
| Predicate | displayCoating |
P81140
|
FINISHED |
| Object | fully laminated display |
—
|
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: fully laminated display | Statement: [iPad Air (4th generation), displayCoating, fully laminated display]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: displayCoating Context triple: [iPad Air (4th generation), displayCoating, fully laminated display]
-
A.
coatingType
chosen
Indicates the type or kind of coating applied to or associated with an entity.
-
B.
decorativeFinish
Indicates that one entity serves as an ornamental or aesthetic surface treatment applied to another entity.
-
C.
skeletonCoating
Indicates that one entity serves as a coating, covering, or outer layer on the skeleton of another entity.
-
D.
primaryMaterialOnDisplay
Indicates that a material is the main or dominant substance featured in the visible presentation or display of an object or item.
-
E.
displays
Indicates that one entity visually presents or shows another entity’s content or information.
- 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_69d6ab4780948190bdb9f7620c2ac27e |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9100b4ca8819084845ca4c13e34ce |
completed | April 10, 2026, 2:58 p.m. |
| PD | Predicate disambiguation | batch_69d902bac9e08190aa1a99c835f29542 |
completed | April 10, 2026, 2:01 p.m. |
Created at: April 8, 2026, 9:47 p.m.