Triple
T27226290
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St Mary’s Church, Fairford |
E682020
|
entity |
| Predicate | windowDate |
P6878
|
FINISHED |
| Object | circa late 15th century |
—
|
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: circa late 15th century | Statement: [St Mary’s Church, Fairford, windowDate, circa late 15th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: windowDate Context triple: [St Mary’s Church, Fairford, windowDate, circa late 15th century]
-
A.
windowArea
Indicates the total surface area occupied by a window (or windows) in a given context.
-
B.
windowType
Indicates the specific kind or category of window associated with an entity.
-
C.
dateOf
chosen
Indicates that one entity specifies the calendar date associated with another entity, such as when it occurred, was created, or is scheduled.
-
D.
dayDepicted
Indicates that a specific day or date is visually or otherwise represented in the subject entity.
-
E.
date
Indicates that two entities are engaged in or participate in a romantic or social outing or relationship with each other.
- 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_69f6264b0bbc8190aca2e1fb1ae773fd |
completed | May 2, 2026, 4:28 p.m. |
| PD | Predicate disambiguation | batch_69f620e38aec8190bb184edcdbd6da64 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 9:44 a.m.