Triple

T11185400
Position Surface form Disambiguated ID Type / Status
Subject MP 44 E264652 entity
Predicate manufacturer P490 FINISHED
Object Erma Werke
Erma Werke was a German arms manufacturer best known for producing small arms and submachine guns before and during World War II.
 E910272 NE FINISHED

How this triple was built (4 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: Erma Werke | Statement: [MP 44, manufacturer, Erma Werke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Erma Werke
Context triple: [MP 44, manufacturer, Erma Werke]
  • A. Buna-Werke
    Buna-Werke was a synthetic rubber and fuel plant operated by IG Farben near Auschwitz, notorious for its use of forced labor from the adjacent Monowitz concentration camp during World War II.
  • B. Erla Maschinenwerk
    Erla Maschinenwerk was a German aircraft manufacturing company best known for producing Messerschmitt fighter planes under license during World War II.
  • C. E.S. Mittler & Sohn
    E.S. Mittler & Sohn is a historic German publishing house known for its military and technical literature.
  • D. Lohner-Werke
    Lohner-Werke was an Austrian vehicle manufacturer best known for producing early electric and hybrid cars, including pioneering designs by Ferdinand Porsche.
  • E. Borsigwerke
    Borsigwerke is a Berlin U-Bahn station on line U6 serving the Tegel district in the city’s northwest.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Erma Werke
Triple: [MP 44, manufacturer, Erma Werke]
Generated description
Erma Werke was a German arms manufacturer best known for producing small arms and submachine guns before and during World War II.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Erma Werke
Target entity description: Erma Werke was a German arms manufacturer best known for producing small arms and submachine guns before and during World War II.
  • A. Buna-Werke
    Buna-Werke was a synthetic rubber and fuel plant operated by IG Farben near Auschwitz, notorious for its use of forced labor from the adjacent Monowitz concentration camp during World War II.
  • B. Erla Maschinenwerk
    Erla Maschinenwerk was a German aircraft manufacturing company best known for producing Messerschmitt fighter planes under license during World War II.
  • C. E.S. Mittler & Sohn
    E.S. Mittler & Sohn is a historic German publishing house known for its military and technical literature.
  • D. Lohner-Werke
    Lohner-Werke was an Austrian vehicle manufacturer best known for producing early electric and hybrid cars, including pioneering designs by Ferdinand Porsche.
  • E. Borsigwerke
    Borsigwerke is a Berlin U-Bahn station on line U6 serving the Tegel district in the city’s northwest.
  • F. None of above. chosen

Provenance (5 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_69d6aa9dafac8190bd90d2c74f661aa7 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e8abbeac8190ad6e419258999f4e completed April 9, 2026, 5:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69e483d0f4548190b97c7725a9f7c0e6 completed April 19, 2026, 7:27 a.m.
NEDg Description generation batch_69e48717c35481908fb05597084167e7 completed April 19, 2026, 7:41 a.m.
NED2 Entity disambiguation (via description) batch_69e48875faa88190af33654e6d9a708b completed April 19, 2026, 7:47 a.m.
Created at: April 8, 2026, 9:29 p.m.