Triple
T7291562
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abergavenny Castle |
E164408
|
entity |
| Predicate | laterConstructionMaterial |
P59925
|
FINISHED |
| Object | stone |
—
|
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: stone | Statement: [Abergavenny Castle, laterConstructionMaterial, stone]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterConstructionMaterial Context triple: [Abergavenny Castle, laterConstructionMaterial, stone]
-
A.
laterConstruction
Indicates that one construction event or structure occurred or was built after another in time.
-
B.
constructionUsed
Indicates that one entity was employed as a construction method, material, or component in creating or assembling another entity.
-
C.
materialUsed
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
-
D.
constructionType
Indicates the specific method or style by which something is built or constructed.
-
E.
hasReconstructionMaterial
chosen
Indicates that something is associated with, composed of, or utilizes a particular material for its reconstruction.
- 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_69c6887a499881909dd23341399c59d8 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6eb6e8f3881908628b3d41aad70c6 |
completed | March 27, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69c6e76c5fbc8190b378830082f11cb0 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 3 p.m.