Triple
T8831852
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DZ Bank building |
E210163
|
entity |
| Predicate | occupant |
P75
|
FINISHED |
| Object | DZ Bank |
E761909
|
NE 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: DZ Bank | Statement: [DZ Bank building, occupant, DZ Bank]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DZ Bank Context triple: [DZ Bank building, occupant, DZ Bank]
-
A.
DZ Bank
chosen
DZ Bank is a major German cooperative central bank that serves as the central institution for numerous cooperative banks and financial services providers across Germany.
-
B.
Dresdner Bank
Dresdner Bank was one of Germany’s major commercial banks, historically influential in the country’s financial and industrial development.
-
C.
Danske Bank
Danske Bank is a major Nordic financial institution headquartered in Copenhagen, Denmark, offering a wide range of banking and financial services across Northern Europe.
-
D.
Basler Handelsbank
Basler Handelsbank is a Swiss banking institution historically known for its role in founding the global reinsurance company Swiss Re.
-
E.
Westkreuz
Westkreuz is a major Berlin S-Bahn interchange station that serves as a key junction for multiple suburban rail lines.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca8365b28081909e48e45e95dfc405 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc604ed2b88190b4f53b34b5a438f7 |
completed | April 1, 2026, 12:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfa069d7488190ade4caa15fa83cd9 |
completed | April 3, 2026, 11:11 a.m. |
Created at: March 30, 2026, 6:47 p.m.