Triple
T27226293
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St Mary’s Church, Fairford |
E682020
|
entity |
| Predicate | windowSubject |
P162522
|
FINISHED |
| Object | saints |
—
|
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: saints | Statement: [St Mary’s Church, Fairford, windowSubject, saints]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: windowSubject Context triple: [St Mary’s Church, Fairford, windowSubject, saints]
-
A.
windowSubject
chosen
Indicates that an entity serves as the subject or primary focus associated with a particular window or window-related context.
-
B.
windowType
Indicates the specific kind or category of window associated with an entity.
-
C.
windowArea
Indicates the total surface area occupied by a window (or windows) in a given context.
-
D.
windowManagement
Indicates the relationship or action of controlling, arranging, or interacting with on-screen windows within a graphical user interface.
-
E.
windowManagementProtocol
Indicates a protocol governing how windows are created, arranged, displayed, and controlled within a graphical user interface or windowing system.
- 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_69eefacdad7881908b7bca61c90a1a1e |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f6352fdb788190b9bad30243690743 |
completed | May 2, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69f631850ae08190a0ba51e4f1e4ccb3 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 27, 2026, 9:44 a.m.