Triple
T1724584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Windows 1.0 |
E37467
|
entity |
| Predicate | windowManagement |
P31211
|
FINISHED |
| Object | tiled windows |
—
|
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: tiled windows | Statement: [Windows 1.0, windowManagement, tiled windows]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: windowManagement Context triple: [Windows 1.0, windowManagement, tiled windows]
-
A.
windowType
Indicates the specific kind or category of window associated with an entity.
-
B.
userInterface
Indicates a relationship where one entity serves as the interface or interaction layer through which a user engages with another system, service, or resource.
-
C.
frameworkPresented
Indicates that a particular framework has been formally introduced or shown to an audience or recipient.
-
D.
operatingSystem
Indicates that one entity is the operating system running on, or used by, another entity.
-
E.
monitors
Indicates that one entity observes, tracks, or checks the state, behavior, or performance of another entity over time.
- F. None of above. chosen
Provenance (4 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_69a8861acab88190bb43cde203429399 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aadb7bda1081908f2c41c520c9c55c |
completed | March 6, 2026, 1:49 p.m. |
| PD | Predicate disambiguation | batch_69aa61c0a0288190bce9d60062a84b69 |
completed | March 6, 2026, 5:10 a.m. |
| PDg | Predicate description generation | batch_69aadb68868c819097ec6db6194abae6 |
completed | March 6, 2026, 1:49 p.m. |
Created at: March 4, 2026, 7:30 p.m.