Triple
T17164062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Metz Cathedral |
E416558
|
entity |
| Predicate | windowArea |
P126353
|
FINISHED |
| Object | about 6,500 square metres of 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: about 6,500 square metres of stained glass | Statement: [Metz Cathedral, windowArea, about 6,500 square metres of stained glass]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: windowArea Context triple: [Metz Cathedral, windowArea, about 6,500 square metres of stained glass]
-
A.
windowManagement
Indicates the relationship or action of controlling, arranging, or interacting with on-screen windows within a graphical user interface.
-
B.
windowType
Indicates the specific kind or category of window associated with an entity.
-
C.
windowManagementProtocol
Indicates a protocol governing how windows are created, arranged, displayed, and controlled within a graphical user interface or windowing system.
-
D.
panelArea
Indicates the total surface area covered or occupied by a specific panel.
-
E.
windowManagementStyle
Indicates how windows are organized, displayed, and controlled within a user interface or system.
- 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_69d886d279c081909f8ff1f743ddeb69 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f913c84481908bb5da8bcc6a2e62 |
completed | April 18, 2026, 9:35 p.m. |
| PD | Predicate disambiguation | batch_69e3830d2a90819092386717dc56f0e8 |
completed | April 18, 2026, 1:11 p.m. |
| PDg | Predicate description generation | batch_69e3873f62108190966c4e741ebd548d |
completed | April 18, 2026, 1:29 p.m. |
Created at: April 10, 2026, 5:37 a.m.