Triple

T7047424
Position Surface form Disambiguated ID Type / Status
Subject Hermann Pohlmann E163675 entity
Predicate employer P7 FINISHED
Object Junkers E44318 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: Junkers | Statement: [Hermann Pohlmann, employer, Junkers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Junkers
Context triple: [Hermann Pohlmann, employer, Junkers]
  • A. Junkers chosen
    Junkers was a pioneering German aircraft manufacturer renowned for producing innovative military and civilian airplanes, particularly during the early to mid-20th century.
  • B. Heinkel
    Heinkel was a German aircraft manufacturing company best known for producing military aircraft for Nazi Germany during World War II.
  • C. Dornier Flugzeugwerke
    Dornier Flugzeugwerke was a German aircraft manufacturer best known for producing military aircraft for the Luftwaffe before and during World War II.
  • D. Albatros Flugzeugwerke
    Albatros Flugzeugwerke was a German aircraft manufacturer best known for producing several important fighter planes for the German air service during World War I.
  • E. Arado Flugzeugwerke
    Arado Flugzeugwerke was a German aircraft manufacturer best known for producing military planes for the Luftwaffe during World War II, including pioneering jet-powered designs.
  • 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_69c6885f598c8190b6b6495c59d8d962 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e24c4004819086002bfe55502374 completed March 27, 2026, 8:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69c794429b648190b6399a2447db07d0 completed March 28, 2026, 8:41 a.m.
Created at: March 27, 2026, 2:37 p.m.