Triple
T7203723
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nespresso |
E148612
|
entity |
| Predicate | capsuleSystem |
P75801
|
FINISHED |
| Object | proprietary coffee capsule system |
—
|
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: proprietary coffee capsule system | Statement: [Nespresso, capsuleSystem, proprietary coffee capsule system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capsuleSystem Context triple: [Nespresso, capsuleSystem, proprietary coffee capsule system]
-
A.
capsule
Indicates that one entity is a capsule containing, enclosing, or encapsulating another entity.
-
B.
capsuleRecovery
Indicates the action or process of retrieving a capsule after its use, mission, or deployment.
-
C.
capsuleName
Indicates that an entity has the specified name or label of a capsule (such as a pill, container, or encapsulated unit).
-
D.
capsuleLost
Indicates that a capsule that was previously possessed, controlled, or expected is no longer in the owner’s possession and its whereabouts are unknown.
-
E.
capsuleSerialNumber
Indicates that a capsule is associated with a specific identifying serial number.
- F. None of above. chosen
Provenance (4 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_69c687e8cf188190b5f3ecffd681f04e |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6e94bfb2c81909ab492757435fce4 |
completed | March 27, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69c6e757fed4819091b0a096e3befc3a |
completed | March 27, 2026, 8:23 p.m. |
| PDg | Predicate description generation | batch_69c6e8fd9b848190b2b1beea5698422b |
completed | March 27, 2026, 8:30 p.m. |
Created at: March 27, 2026, 2:52 p.m.