Triple
T2136910
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Waterloo Bridge |
E46673
|
entity |
| Predicate | hasParapetMaterial |
P18960
|
FINISHED |
| Object | Portland 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: Portland stone | Statement: [Waterloo Bridge, hasParapetMaterial, Portland stone]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasParapetMaterial Context triple: [Waterloo Bridge, hasParapetMaterial, Portland stone]
-
A.
hasParapet
chosen
Indicates that an object, structure, or area is equipped with or bounded by a parapet (a low protective wall or barrier along an edge).
-
B.
exteriorMaterial
Indicates the material that forms the outer surface or outer construction of an object or structure.
-
C.
hasBalustrades
Indicates that one entity features or is equipped with balustrades as part of its structure or design.
-
D.
hasHandrails
Indicates that an object, structure, or pathway is equipped with handrails for support or safety.
-
E.
wallMaterial
Indicates that one entity is the material from which a wall or walls of another entity are constructed.
- 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_69a88a174ab48190a5db20c132e5dccf |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abbf74147c81908793c3694894f94a |
completed | March 7, 2026, 6:02 a.m. |
| PD | Predicate disambiguation | batch_69abbd96a3b0819081efbfef975e1513 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:44 p.m.