Triple
T15255332
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Google Cloud project |
E364630
|
entity |
| Predicate | scopeOf |
P61710
|
FINISHED |
| Object | IAM roles |
—
|
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: IAM roles | Statement: [Google Cloud project, scopeOf, IAM roles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scopeOf Context triple: [Google Cloud project, scopeOf, IAM roles]
-
A.
scopeType
Indicates the specific range, level, or context within which a given relationship, rule, or action is defined or applies.
-
B.
scopeOfReference
chosen
Indicates the range or domain of things, concepts, or entities to which a reference, statement, or expression applies.
-
C.
scopeOfControl
Indicates the extent or range within which an entity has authority, influence, or control over another entity or set of entities.
-
D.
scopeOfAdvice
Indicates that one entity defines or specifies the range, boundaries, or subject matter covered by another entity’s advice or guidance.
-
E.
scopeDefinedBy
Indicates that the extent or boundaries of one entity’s applicability, influence, or validity are determined or constrained by 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_69d85a0dde7481908fc64d1e82d5d20d |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e007f8cb308190933c4478aa096e24 |
completed | April 15, 2026, 9:49 p.m. |
| PD | Predicate disambiguation | batch_69deca8d1bd48190a4b94f29b425e335 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:13 a.m.