Triple
T18969294
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Union Church of Pocantico Hills |
E464124
|
entity |
| Predicate | hasWindowStyle |
P133988
|
FINISHED |
| Object | modernist stained glass |
—
|
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: modernist stained glass | Statement: [Union Church of Pocantico Hills, hasWindowStyle, modernist stained glass]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWindowStyle Context triple: [Union Church of Pocantico Hills, hasWindowStyle, modernist stained glass]
-
A.
windowManagementStyle
Indicates how windows are organized, displayed, and controlled within a user interface or system.
-
B.
hasSystemStyle
Indicates that one entity is associated with, or characterized by, a particular system-defined style of another entity.
-
C.
hasWindowsShape
Indicates that an object possesses a particular geometric or stylistic form characteristic of windows.
-
D.
hasRoseWindow
Indicates that an entity features or includes a rose window as part of its structure.
-
E.
supportsWindowedMode
Indicates that an entity provides or allows operation in a windowed (non-fullscreen) display mode.
- 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_69d8dcffc278819086792a4ebfddfafa |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d618e2ec8190848a41733e6db2f1 |
completed | April 20, 2026, 7:30 a.m. |
| PD | Predicate disambiguation | batch_69e4a2f437648190b85650dae8885d48 |
completed | April 19, 2026, 9:40 a.m. |
| PDg | Predicate description generation | batch_69e4ad8e075c8190ad561edc5e520057 |
completed | April 19, 2026, 10:25 a.m. |
Created at: April 10, 2026, noon