Triple

T11380722
Position Surface form Disambiguated ID Type / Status
Subject German 5th Army E269585 entity
Predicate notableCommander P1197 FINISHED
Object Karl von Einem E825256 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: Karl von Einem | Statement: [German 5th Army, notableCommander, Karl von Einem]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karl von Einem
Context triple: [German 5th Army, notableCommander, Karl von Einem]
  • A. Karl von Einem chosen
    Karl von Einem was a German general and statesman who served as Prussian Minister of War in the early 20th century, playing a key role in the military buildup preceding World War I.
  • B. Hans von Dohnanyi
    Hans von Dohnanyi was a German jurist and key member of the anti-Nazi resistance who helped document Nazi crimes and was executed by the regime in 1945.
  • C. Emil von Sauer
    Emil von Sauer was a renowned late-Romantic German pianist, composer, and influential piano teacher, celebrated as one of Franz Liszt’s most distinguished students.
  • D. Franz Hössler
    Franz Hössler was a Nazi SS officer and concentration camp official who was tried and executed for war crimes committed during the Holocaust.
  • E. Alfred Koerner
    Alfred Koerner was an architect known for his work on the Berlin Botanical Garden.
  • 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_69d6aacca1048190b39dbbc2174616fa completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7fc331f188190a7f69f1aae53fb6b completed April 9, 2026, 7:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69e556a99c8c8190b7439a548216e648 completed April 19, 2026, 10:26 p.m.
Created at: April 8, 2026, 9:34 p.m.