Triple
T708449
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Windsor Castle |
E14153
|
entity |
| Predicate | builtAs |
P3565
|
FINISHED |
| Object | motte-and-bailey castle |
—
|
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: motte-and-bailey castle | Statement: [Windsor Castle, builtAs, motte-and-bailey castle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: builtAs Context triple: [Windsor Castle, builtAs, motte-and-bailey castle]
-
A.
builtFrom
Indicates that one entity is constructed, composed, or formed using another entity as its material, component, or source.
-
B.
builtOn
Indicates that one entity is constructed, developed, or established using another entity as its base, foundation, or underlying platform.
-
C.
constructedAs
chosen
Indicates that one entity is built, formed, or created in the manner, structure, or configuration specified by another entity.
-
D.
builder
Indicates that an entity is responsible for constructing, creating, or assembling another entity.
-
E.
isBuiltFor
Indicates that one entity is specifically designed, intended, or optimized to serve, support, or accommodate another entity or purpose.
- 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_69a493494ec48190ae6751683625a9ba |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a5c011948190b2cfccd8fe722742 |
completed | March 1, 2026, 8:46 p.m. |
| PD | Predicate disambiguation | batch_69a4a4f0217081908268b3f47e72f8df |
completed | March 1, 2026, 8:43 p.m. |
Created at: March 1, 2026, 7:36 p.m.