Triple
T36332103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaispeicher A |
E894677
|
entity |
| Predicate | structuralBaseFor |
P2421
|
FINISHED |
| Object | Elbphilharmonie |
—
|
NE NERFINISHED |
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: Elbphilharmonie | Statement: [Kaispeicher A, structuralBaseFor, Elbphilharmonie]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: structuralBaseFor Context triple: [Kaispeicher A, structuralBaseFor, Elbphilharmonie]
-
A.
associatedBase
Indicates a relationship where one entity is linked or connected to a corresponding base entity that it depends on or is derived from.
-
B.
basisType
Indicates the type or category of foundational support or underlying structure on which something is based.
-
C.
isBaseFor
chosen
Indicates that one entity serves as the foundational support, starting point, or underlying basis upon which another entity is built, developed, or depends.
-
D.
baseType
Indicates that one entity serves as the underlying or parent type from which another entity is derived or specialized.
-
E.
basingConcept
Indicates that one concept serves as the foundational basis or underlying rationale for another concept.
- 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_69f76e4dcf088190a6c3216c209cab52 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7bb3ff1b08190802b1063d55d3923 |
completed | May 3, 2026, 9:16 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a611a081908dd6aec1df3f4d7f |
completed | May 3, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:09 p.m.