Triple
T21415448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Conisbrough Castle |
E528288
|
entity |
| Predicate | keepHeight |
P9788
|
FINISHED |
| Object | approximately 28 metres |
—
|
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: approximately 28 metres | Statement: [Conisbrough Castle, keepHeight, approximately 28 metres]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keepHeight Context triple: [Conisbrough Castle, keepHeight, approximately 28 metres]
-
A.
hasHeight
chosen
Indicates that one entity possesses a specific vertical measurement or stature.
-
B.
heightContext
Indicates a contextual or situational relationship that specifies how an entity’s height is defined, measured, or interpreted in a particular setting or frame of reference.
-
C.
keptIn
Indicates that one entity is stored, contained, or maintained inside another entity as its location or container.
-
D.
originalHeight
Indicates the initial or starting height of an entity before any change, adjustment, or transformation occurs.
-
E.
typicalHeight
Indicates the usual or characteristic height associated with an entity, such as a person, object, or species.
- 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.