Triple
T18632930
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Bank of Denmark building |
E455466
|
entity |
| Predicate | refinedDetailing |
P132102
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [National Bank of Denmark building, refinedDetailing, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refinedDetailing Context triple: [National Bank of Denmark building, refinedDetailing, yes]
-
A.
refinedIn
Indicates that one entity is processed or purified within a refining facility or operation to improve its quality or extract desired components.
-
B.
refinementBy
Indicates that one entity serves as a more detailed, precise, or improved version of another entity.
-
C.
visualDetail
chosen
Indicates that one entity provides or specifies the visual characteristics, features, or appearance details of another entity.
-
D.
refinedConcept
Indicates that one concept is a more precise, detailed, or specialized version of another concept.
-
E.
semanticsDetail
Indicates a more specific or fine-grained semantic characterization or nuance of a broader meaning or interpretation.
- 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_69d8d38cc7948190a55ea64e5638994e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e54fc5c7ec8190ab0c64f009583f96 |
completed | April 19, 2026, 9:57 p.m. |
| PD | Predicate disambiguation | batch_69e478d4a7948190a4bb9223bb5dddfc |
completed | April 19, 2026, 6:40 a.m. |
Created at: April 10, 2026, 11:46 a.m.