Triple

T2999782
Position Surface form Disambiguated ID Type / Status
Subject Wilhelm Maybach E81157 entity
Predicate employer P7 FINISHED
Object Deutz AG
Deutz AG is a German manufacturer best known for producing internal combustion engines, particularly for industrial and agricultural applications.
 E318785 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: Deutz AG | Statement: [Wilhelm Maybach, employer, Deutz AG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Deutz AG
Context triple: [Wilhelm Maybach, employer, Deutz AG]
  • A. Krauss-Maffei Wegmann
    Krauss-Maffei Wegmann is a German defense company specializing in the design and production of armored vehicles and military land systems.
  • B. Borsigwerke
    Borsigwerke is a Berlin U-Bahn station on line U6 serving the Tegel district in the city’s northwest.
  • C. Voith
    Voith is a German multinational engineering company known for its technologies and services in sectors such as energy, paper, raw materials, and transportation.
  • D. Steyr-Daimler-Puch
    Steyr-Daimler-Puch was a major Austrian industrial conglomerate best known for producing firearms, vehicles, and machinery throughout the 20th century.
  • E. Bühler
    Bühler is a German-language surname borne by various notable individuals across fields such as politics, sports, and academia.
  • 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: Deutz AG
Triple: [Wilhelm Maybach, employer, Deutz AG]
Generated description
Deutz AG is a German manufacturer best known for producing internal combustion engines, particularly for industrial and agricultural applications.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Deutz AG
Target entity description: Deutz AG is a German manufacturer best known for producing internal combustion engines, particularly for industrial and agricultural applications.
  • A. Krauss-Maffei Wegmann
    Krauss-Maffei Wegmann is a German defense company specializing in the design and production of armored vehicles and military land systems.
  • B. Borsigwerke
    Borsigwerke is a Berlin U-Bahn station on line U6 serving the Tegel district in the city’s northwest.
  • C. Voith
    Voith is a German multinational engineering company known for its technologies and services in sectors such as energy, paper, raw materials, and transportation.
  • D. Steyr-Daimler-Puch
    Steyr-Daimler-Puch was a major Austrian industrial conglomerate best known for producing firearms, vehicles, and machinery throughout the 20th century.
  • E. Bühler
    Bühler is a German-language surname borne by various notable individuals across fields such as politics, sports, and academia.
  • 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_69ad8b187fc8819085914d3c9ea3142d completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad99f8eb248190b50fd539a06a5a62 completed March 8, 2026, 3:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69b12e4b54188190bf900bf10061a57a completed March 11, 2026, 8:56 a.m.
NEDg Description generation batch_69b12f188c7c81908d1d575252dc4bda completed March 11, 2026, 9 a.m.
NED2 Entity disambiguation (via description) batch_69b1c9bccb3081909e6869b5cba68117 completed March 11, 2026, 7:59 p.m.
Created at: March 8, 2026, 2:59 p.m.