Triple
T20009325
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cotswold vernacular architecture |
E494544
|
entity |
| Predicate | doorSurroundDetail |
P77408
|
FINISHED |
| Object | simple stone lintels |
—
|
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: simple stone lintels | Statement: [Cotswold vernacular architecture, doorSurroundDetail, simple stone lintels]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: doorSurroundDetail Context triple: [Cotswold vernacular architecture, doorSurroundDetail, simple stone lintels]
-
A.
doorAndWindowDetail
Indicates a relationship that specifies detailed characteristics or features shared by both doors and windows.
-
B.
doorConfiguration
Indicates how a door is arranged or set up in relation to its frame, opening direction, and operational characteristics.
-
C.
doorwayFeature
chosen
Indicates that one entity is a feature, characteristic, or structural element specifically associated with a doorway of another entity.
-
D.
hasDoorMaterial
Indicates that an entity’s door is made of, or primarily composed of, a specified material.
-
E.
doorType
Indicates the specific kind or category of door associated with an entity.
- 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_69da626b2d748190886981ea90c8b2ea |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e661a81c5881909692fcaaf59a57c9 |
completed | April 20, 2026, 5:26 p.m. |
| PD | Predicate disambiguation | batch_69e54cdddbd48190becc8b2aa5ab4ef9 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:33 p.m.