Triple

T15874883
Position Surface form Disambiguated ID Type / Status
Subject Aktion 1005 E384927 entity
Predicate organizer P123 FINISHED
Object Paul Blobel E79188 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: Paul Blobel | Statement: [Aktion 1005, organizer, Paul Blobel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Blobel
Context triple: [Aktion 1005, organizer, Paul Blobel]
  • A. Paul Blobel chosen
    Paul Blobel was a high-ranking Nazi SS officer and war criminal best known for organizing and overseeing mass executions, including the Babi Yar massacre, during the Holocaust.
  • B. Udo Proksch
    Udo Proksch was an Austrian businessman and socialite notorious for his role in the 1977 "Lucona" insurance fraud and murder case, one of Austria's most infamous postwar scandals.
  • C. Wolfgang Ehrlich
    Wolfgang Ehrlich is a notable individual who shares the Ehrlich surname, recognized enough to be specifically cited as a bearer of the name.
  • D. Klaus Blaum
    Klaus Blaum is a German physicist renowned for his pioneering work in precision measurements of atomic and nuclear properties using ion traps.
  • E. Juergen Weigert
    Juergen Weigert is a software developer best known for his significant contributions to the GNU Screen terminal multiplexer project.
  • 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_69d86da4e86481909f1325fdc971b5ec completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e155fcffbc8190ba6d133107b83a7f completed April 16, 2026, 9:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb59ddc488190ae6b6913f85005f6 completed May 9, 2026, 10:30 p.m.
Created at: April 10, 2026, 4:51 a.m.