Triple
T9622601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karl Helfferich |
E232379
|
entity |
| Predicate | employer |
P7
|
FINISHED |
| Object | Deutsche Bank |
E373967
|
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: Deutsche Bank | Statement: [Karl Helfferich, employer, Deutsche Bank]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Deutsche Bank Context triple: [Karl Helfferich, employer, Deutsche Bank]
-
A.
Deutsche Bank
chosen
Deutsche Bank is a major global investment bank and financial services company headquartered in Frankfurt, Germany.
-
B.
Commerzbank AG
Commerzbank AG is a major German commercial bank headquartered in Frankfurt, known as one of the country’s leading financial institutions serving corporate, institutional, and retail clients.
-
C.
Dresdner Bank
Dresdner Bank was one of Germany’s major commercial banks, historically influential in the country’s financial and industrial development.
-
D.
Citigroup
Citigroup is a major American multinational investment bank and financial services corporation headquartered in New York City.
-
E.
ABN AMRO
ABN AMRO is a major Dutch bank headquartered in Amsterdam, known for providing a wide range of retail, private, and corporate banking services internationally.
- 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_69ca848793ec8190a93a12383a754dc0 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9ad505588190b8c81ce09f1904ec |
completed | April 1, 2026, 10:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1797386d88190bc1d9309ecc1b4fb |
completed | April 4, 2026, 8:49 p.m. |
Created at: March 30, 2026, 8:10 p.m.