Triple
T3721162
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Werderscher Markt 1, Berlin |
E81639
|
entity |
| Predicate | buildingComplexType |
P17911
|
FINISHED |
| Object | block-filling administrative complex |
—
|
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: block-filling administrative complex | Statement: [Werderscher Markt 1, Berlin, buildingComplexType, block-filling administrative complex]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: buildingComplexType Context triple: [Werderscher Markt 1, Berlin, buildingComplexType, block-filling administrative complex]
-
A.
buildingComplex
chosen
Indicates a relationship where multiple buildings are grouped and function together as a single integrated complex.
-
B.
building
Indicates that one entity constructs, assembles, or develops another entity, typically over a period of time.
-
C.
buildingSystem
Indicates that one entity functions as a system, subsystem, or organized set of components that serves or supports the operation of a building.
-
D.
buildingSection
Indicates a relationship where one entity is a specific section, part, or subdivision of a larger building.
-
E.
buildingType
Indicates the specific category or function that characterizes what kind of building something is.
- 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_69ad8b1b7ef081908d2d381bbf54985a |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adca9d29208190bbf38a6aa88f954a |
completed | March 8, 2026, 7:14 p.m. |
| PD | Predicate disambiguation | batch_69adc0436e508190909ec4a3e8443aef |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:34 p.m.