Triple

T509970
Position Surface form Disambiguated ID Type / Status
Subject Prussia E10584 entity
Predicate leader P981 FINISHED
Object Otto von Bismarck E29110 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: Otto von Bismarck | Statement: [Prussia, leader, Otto von Bismarck]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Otto von Bismarck
Context triple: [Prussia, leader, Otto von Bismarck]
  • A. Otto von Bismarck chosen
    Otto von Bismarck was a 19th-century Prussian statesman who engineered the unification of Germany and served as the first Chancellor of the German Empire.
  • B. Roman Herzog
    Roman Herzog was a German jurist and politician who served as President of Germany from 1994 to 1999.
  • C. Konrad Adenauer
    Konrad Adenauer was a German statesman who led the postwar reconstruction and Western integration of Germany, serving as a key architect of modern German democracy and European unity.
  • D. Gustav Stresemann
    Gustav Stresemann was a German statesman and Nobel Peace Prize–winning foreign minister of the Weimar Republic, known for his efforts at post–World War I reconciliation and stabilizing Germany’s international position.
  • E. Friedrich
    Friedrich is the given first name of the German philosopher, logician, and mathematician Gottlob Frege.
  • 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_69a2e848adf881908e5e04f7af030093 completed Feb. 28, 2026, 1:06 p.m.
NER Named-entity recognition batch_69a2f164a9d48190b525a97b5c06ffe2 completed Feb. 28, 2026, 1:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69a49ebaf5c48190b24614b2a1ab9466 completed March 1, 2026, 8:16 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.