Triple
T22695541
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CMS computing grid |
E561162
|
entity |
| Predicate | supportsUsersFrom |
P55187
|
FINISHED |
| Object | multiple countries |
—
|
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: multiple countries | Statement: [CMS computing grid, supportsUsersFrom, multiple countries]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsUsersFrom Context triple: [CMS computing grid, supportsUsersFrom, multiple countries]
-
A.
supportsUsers
Indicates that one entity provides assistance, functionality, or compatibility for the users associated with another entity.
-
B.
supportedFrom
Indicates that one entity provides backing, assistance, or justification for another entity, often serving as the source or basis of that support.
-
C.
supportsUserServices
Indicates that one entity provides the necessary functionality or resources for user-facing services to operate or be delivered.
-
D.
supportsUserType
chosen
Indicates that one entity is compatible with, or provides functionality for, a specified type or category of user.
-
E.
supportsUse
Indicates that one entity enables, allows, or is compatible with the use or operation of 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_69e2454e615481909c177440be559d2c |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1789e05d88190b9d51bb3f8e3e9d4 |
completed | April 29, 2026, 3:18 a.m. |
| PD | Predicate disambiguation | batch_69ee62bd657c81909f7b01245b080a5f |
completed | April 26, 2026, 7:08 p.m. |
Created at: April 17, 2026, 3:14 p.m.