Triple

T22239393
Position Surface form Disambiguated ID Type / Status
Subject DB1 E549679 entity
Predicate represents P129 FINISHED
Object Deutsche Börse AG 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: Deutsche Börse AG | Statement: [DB1, represents, Deutsche Börse AG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Deutsche Börse AG
Context triple: [DB1, represents, Deutsche Börse AG]
  • A. Deutsche Börse chosen
    Deutsche Börse is a major German financial services company that operates stock exchanges and provides market infrastructure, trading, and clearing services globally.
  • B. Deutscher Börsenverein
    Deutscher Börsenverein is the German Publishers and Booksellers Association, a key industry organization representing the interests of the book trade in Germany.
  • C. Frankfurt Stock Exchange
    The Frankfurt Stock Exchange is one of the world’s largest and most important securities trading centers, serving as Germany’s primary stock market.
  • D. Berliner Börse
    The Berliner Börse was Berlin’s historic stock exchange building, a prominent 19th-century financial and architectural landmark designed by Friedrich Hitzig.
  • E. Mannheim stock exchange
    The Mannheim stock exchange was a regional securities market in Mannheim, Germany, historically significant as an early trading venue for industrial companies such as Benz & Cie.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e4102b881909cf47d3768e25c19 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f132123a048190ba5a90d7acb9aeb2 completed April 28, 2026, 10:17 p.m.
Created at: April 16, 2026, 8:38 p.m.