Triple

T14996379
Position Surface form Disambiguated ID Type / Status
Subject Deutsche Bank E373967 entity
Predicate tickerSymbol P1447 FINISHED
Object DBK
DBK is the stock ticker symbol for Deutsche Bank, a major global investment and financial services institution based in Germany.
E1131242 NE FINISHED

How this triple was built (4 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: DBK | Statement: [Deutsche Bank, tickerSymbol, DBK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: DBK
Context triple: [Deutsche Bank, tickerSymbol, DBK]
  • A. DBK
    DBK is the commonly used abbreviation for the German Bishops' Conference, the assembly of Catholic bishops in Germany.
  • B. DB1
    DB1 is the stock ticker symbol for Deutsche Börse AG, a major German exchange organization that operates the Frankfurt Stock Exchange and related financial market infrastructure.
  • C. BDB
    BDB is the IATA airport code for Bundaberg Airport, a regional airport serving the city of Bundaberg in Queensland, Australia.
  • D. DBU
    DBU is the Danish Football Association, the governing body responsible for organizing and overseeing football activities and national teams in Denmark.
  • E. DBM
    DBM is a demand-side platform from Google’s DoubleClick suite that enables advertisers to buy and manage programmatic display, video, and mobile ad inventory across multiple exchanges.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: DBK
Triple: [Deutsche Bank, tickerSymbol, DBK]
Generated description
DBK is the stock ticker symbol for Deutsche Bank, a major global investment and financial services institution based in Germany.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: DBK
Target entity description: DBK is the stock ticker symbol for Deutsche Bank, a major global investment and financial services institution based in Germany.
  • A. DBK
    DBK is the commonly used abbreviation for the German Bishops' Conference, the assembly of Catholic bishops in Germany.
  • B. DB1
    DB1 is the stock ticker symbol for Deutsche Börse AG, a major German exchange organization that operates the Frankfurt Stock Exchange and related financial market infrastructure.
  • C. BDB
    BDB is the IATA airport code for Bundaberg Airport, a regional airport serving the city of Bundaberg in Queensland, Australia.
  • D. DBU
    DBU is the Danish Football Association, the governing body responsible for organizing and overseeing football activities and national teams in Denmark.
  • E. DBM
    DBM is a demand-side platform from Google’s DoubleClick suite that enables advertisers to buy and manage programmatic display, video, and mobile ad inventory across multiple exchanges.
  • F. None of above. chosen

Provenance (5 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_69d85ccc84388190aa151e5173370c8d completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded718e4288190b5e144f82299a194 completed April 15, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe969a63f081908bf11783e2a51229 completed May 9, 2026, 2:06 a.m.
NEDg Description generation batch_69fe97609b3481908ed481f9f061b148 completed May 9, 2026, 2:09 a.m.
NED2 Entity disambiguation (via description) batch_69fe980155748190aef4ce876f985ef2 completed May 9, 2026, 2:12 a.m.
Created at: April 10, 2026, 2:53 a.m.