Triple

T6526573
Position Surface form Disambiguated ID Type / Status
Subject Hildy Beyeler E151317 entity
Predicate spouse P13 FINISHED
Object Ernst Beyeler E194081 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: Ernst Beyeler | Statement: [Hildy Beyeler, spouse, Ernst Beyeler]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ernst Beyeler
Context triple: [Hildy Beyeler, spouse, Ernst Beyeler]
  • A. Ernst Beyeler chosen
    Ernst Beyeler was a prominent Swiss art dealer and collector who co-founded Art Basel and built one of the world’s most important collections of modern art.
  • B. Marcel Beyer
    Marcel Beyer is a contemporary German writer and poet known for his innovative prose and explorations of history, memory, and language.
  • C. Otto de la Roche
    Otto de la Roche was a Burgundian nobleman and crusader who became the first Frankish ruler of the Duchy of Athens after the Fourth Crusade.
  • D. Hugo Eberlein
    Hugo Eberlein was a German communist politician and revolutionary who was a founding figure of the early German communist movement.
  • E. Hermann Becker-Freyseng
    Hermann Becker-Freyseng was a German physician and Luftwaffe medical officer who was convicted as a war criminal for his role in Nazi human experimentation during the Doctors' Trial at Nuremberg.
  • 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_69c687f522748190b3058405553cdabd completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6ada8a0e48190947616f3a09a2cba completed March 27, 2026, 4:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7488992c48190a59b277f65cd0b36 completed March 28, 2026, 3:18 a.m.
Created at: March 27, 2026, 1:45 p.m.