Triple
T24928515
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adobe Sensei |
E618926
|
entity |
| Predicate | appliesDomain |
P1129
|
FINISHED |
| Object | computer vision |
—
|
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: computer vision | Statement: [Adobe Sensei, appliesDomain, computer vision]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliesDomain Context triple: [Adobe Sensei, appliesDomain, computer vision]
-
A.
appliesAcross
Indicates that a condition, rule, or property holds uniformly over multiple items, cases, or contexts.
-
B.
abstractDomain
Indicates that one domain or conceptual space is a higher-level, generalized abstraction of another more concrete or specific domain.
-
C.
appliesVia
Indicates that an action, rule, or effect is carried out, implemented, or achieved through a specified method, medium, or mechanism.
-
D.
appliesTo
chosen
Indicates that something is relevant, valid, or has effect in relation to a particular entity, case, or context.
-
E.
appliedAs
Indicates that one entity submitted itself or was put forward for consideration in a particular role, position, or context relative to another entity.
- 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_69e2fab9edd88190b86004a78a28bc20 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f55e519978819087a1676564a74630 |
completed | May 2, 2026, 2:15 a.m. |
| PD | Predicate disambiguation | batch_69f4a0edd10c81908a052ab864d57c54 |
completed | May 1, 2026, 12:47 p.m. |
Created at: April 18, 2026, 5:29 a.m.