Triple
T28023608
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Local Group Policy Editor |
E707751
|
entity |
| Predicate | policyCategories |
P55606
|
FINISHED |
| Object | Computer Configuration |
—
|
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 Configuration | Statement: [Local Group Policy Editor, policyCategories, Computer Configuration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: policyCategories Context triple: [Local Group Policy Editor, policyCategories, Computer Configuration]
-
A.
policyCategory
chosen
Indicates the classification or type of policy under which an item, rule, or action is grouped.
-
B.
protectionCategory
Indicates a classification relationship where an entity is assigned to a specific type or level of protection based on defined protective criteria or rules.
-
C.
policyTopic
Indicates that one entity is about, concerned with, or categorized under a particular policy-related subject or theme.
-
D.
protectedCategory
Indicates that one entity is classified under a legally or formally recognized group that is granted special protection from discrimination or adverse treatment.
-
E.
policyTool
Indicates that an entity is a tool, mechanism, or instrument used to design, implement, or enforce a policy.
- 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_69ef96baf3a881909a2b63844185dddd |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f674e06c9481909ed0ea736408f0d7 |
completed | May 2, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69f673c2f81c8190bf369226306eef09 |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 27, 2026, 8:11 p.m.