Triple

T20260042
Position Surface form Disambiguated ID Type / Status
Subject Bölkow E498808 entity
Predicate hasKeyPerson P256 FINISHED
Object Ludwig Bölkow 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: Ludwig Bölkow | Statement: [Bölkow, hasKeyPerson, Ludwig Bölkow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ludwig Bölkow
Context triple: [Bölkow, hasKeyPerson, Ludwig Bölkow]
  • A. Ludwig Bölkow chosen
    Ludwig Bölkow was a prominent German aerospace engineer and industrialist who played a key role in postwar European aviation and space technology development.
  • B. Henrich Focke
    Henrich Focke was a German aviation engineer and pioneer who co-founded the aircraft manufacturer Focke-Wulf and became a key figure in early helicopter development.
  • C. Heinrich Wörner
    Heinrich Wörner is a German architect best known for designing the main building of the Topography of Terror documentation center in Berlin.
  • D. Erich Bachem
    Erich Bachem was a German aeronautical engineer best known for designing innovative and experimental aircraft during World War II and later contributing to postwar aerospace and industrial design.
  • E. Werner Dettwiler
    Werner Dettwiler is a Swiss businessman best known as the founder of the Swiss medical technology company MDA.
  • 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_69da6275fa6c8190952924930adee150 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e674c90d00819082f68822635ee86a completed April 20, 2026, 6:47 p.m.
Created at: April 11, 2026, 11:41 p.m.