Triple
T1719345
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Windows Firewall |
E37355
|
entity |
| Predicate | runsAs |
P23495
|
FINISHED |
| Object | Windows service |
—
|
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: Windows service | Statement: [Windows Firewall, runsAs, Windows service]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: runsAs Context triple: [Windows Firewall, runsAs, Windows service]
-
A.
runsUnder
chosen
Indicates that one process, task, or component operates within the control, environment, or context provided by another system, platform, or framework.
-
B.
runsFrom
Indicates that one entity flees or escapes away from another entity.
-
C.
runBy
Indicates that an entity is operated, managed, or controlled by another entity.
-
D.
alsoRuns
Indicates that the subject, in addition to its primary or previously mentioned activity or role, performs or operates another activity, process, or entity.
-
E.
runsDirectlyOver
Indicates that one entity passes or extends immediately above another along its length or span, without significant vertical separation or intervening structures.
- 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_69a8861912dc8190931af43b4b9158a7 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69ab5c96db6c8190a745d6fef7bf2cdb |
completed | March 6, 2026, 11 p.m. |
| PD | Predicate disambiguation | batch_69aa61bed2fc819086d912cd34285978 |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:30 p.m.