Triple
T7858236
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Disk Cleanup |
E182429
|
entity |
| Predicate | executablePathPattern |
P31927
|
FINISHED |
| Object | C:\\Windows\\System32\\cleanmgr.exe |
—
|
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: C:\\Windows\\System32\\cleanmgr.exe | Statement: [Disk Cleanup, executablePathPattern, C:\\Windows\\System32\\cleanmgr.exe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: executablePathPattern Context triple: [Disk Cleanup, executablePathPattern, C:\\Windows\\System32\\cleanmgr.exe]
-
A.
executableName
chosen
Indicates the specific name of a program or binary file that is intended to be executed.
-
B.
applicationLocation
Indicates the place or environment where an application is deployed, used, or made available.
-
C.
launcherType
Indicates the specific kind or category of launcher associated with or used in relation to an entity.
-
D.
launchLocation
Indicates the place or site from which something is launched or set into motion.
-
E.
autoIconLocation
Indicates that an icon’s position is determined automatically rather than being manually specified.
- 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_69ca82887fd48190975896bf38c4596b |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb1a76f8648190976b488d0d8658ef |
completed | March 31, 2026, 12:51 a.m. |
| PD | Predicate disambiguation | batch_69cae925ca388190ae4a01fa76e957e8 |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 4:52 p.m.