Triple
T35074413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Box House |
E1011970
|
entity |
| Predicate | hasTypicalWindowType |
P8656
|
FINISHED |
| Object | double-hung sash 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: double-hung sash windows | Statement: [Box House, hasTypicalWindowType, double-hung sash windows]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypicalWindowType Context triple: [Box House, hasTypicalWindowType, double-hung sash windows]
-
A.
hasWindowStyle
Indicates that an entity possesses or is characterized by a particular style or type of window.
-
B.
windowType
chosen
Indicates the specific kind or category of window associated with an entity.
-
C.
hasTypicalEntranceWindow
Indicates that there is a commonly occurring or standard time interval during which entrance or admission typically takes place.
-
D.
hasWindowBorderStyle
Indicates the specific style or appearance of the border surrounding a window.
-
E.
typicalApplicationWindow
Indicates that something is a standard or commonly used application window in a software environment.
- 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_69f76dd193108190af2528186f25b72a |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ff5f5ecc808190b2df364da108ff4c |
completed | May 9, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_69ff5b84131c8190bf81d7fb53e934bc |
completed | May 9, 2026, 4:06 p.m. |
Created at: May 3, 2026, 4:01 p.m.