Triple
T14890238
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poitiers Cathedral |
E359735
|
entity |
| Predicate | hasStainedGlassWindow |
P45751
|
FINISHED |
| Object | 12th-century lancet 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: 12th-century lancet windows | Statement: [Poitiers Cathedral, hasStainedGlassWindow, 12th-century lancet windows]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStainedGlassWindow Context triple: [Poitiers Cathedral, hasStainedGlassWindow, 12th-century lancet windows]
-
A.
hasStainedGlass
chosen
Indicates that one entity possesses or features stained glass as part of its structure or design.
-
B.
hasStainedGlassManufacturer
Indicates that one entity serves as the manufacturer responsible for producing the stained glass associated with another entity.
-
C.
numberOfStainedGlassPanels
Indicates the count of stained glass panels associated with a given entity or object.
-
D.
stainedGlassArtist
Indicates that one entity is a stained glass artist who creates or designs stained glass works in relation to another entity.
-
E.
hasGlassArea
Indicates that an object or structure possesses a surface or region made of glass.
- 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_69d827980cbc8190a0c569ae3940a1d9 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69ded5f6cf5c8190b6b28f58fafe5d59 |
completed | April 15, 2026, 12:04 a.m. |
| PD | Predicate disambiguation | batch_69de8c1a2bcc81908f914e2e2ced65eb |
completed | April 14, 2026, 6:48 p.m. |
Created at: April 10, 2026, 2:09 a.m.