Triple
T21415449
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Conisbrough Castle |
E528288
|
entity |
| Predicate | keepShape |
P1464
|
FINISHED |
| Object | cylindrical with six external buttresses |
—
|
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: cylindrical with six external buttresses | Statement: [Conisbrough Castle, keepShape, cylindrical with six external buttresses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keepShape Context triple: [Conisbrough Castle, keepShape, cylindrical with six external buttresses]
-
A.
keptIn
Indicates that one entity is stored, contained, or maintained inside another entity as its location or container.
-
B.
shape
chosen
Indicates that one entity has a particular geometric or physical form characterized by the other entity.
-
C.
keptWith
Indicates that one entity is stored, maintained, or held together in association with another entity.
-
D.
coreShape
Indicates that one entity serves as the primary or central shape or geometric form of another entity.
-
E.
seeksToShape
Indicates an entity’s intention or effort to influence, mold, or determine the form, direction, or outcome of another entity or situation.
- 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_69e0c454c248819093425d1099101c09 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee62d16bfc8190a1c08dd9d0c80e02 |
completed | April 26, 2026, 7:09 p.m. |
| PD | Predicate disambiguation | batch_69e61633f8208190a2a849457c4e4198 |
completed | April 20, 2026, 12:04 p.m. |
Created at: April 16, 2026, 5:45 p.m.