Triple

T19549101
Position Surface form Disambiguated ID Type / Status
Subject ThyssenKrupp AG E489151 entity
Predicate hasDivision P35 FINISHED
Object ThyssenKrupp Materials Services — NE NERFINISHED

How this triple was built (3 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: ThyssenKrupp Materials Services | Statement: [ThyssenKrupp AG, hasDivision, ThyssenKrupp Materials Services]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ThyssenKrupp Materials Services
Context triple: [ThyssenKrupp AG, hasDivision, ThyssenKrupp Materials Services]
  • A. ThyssenKrupp AG
    ThyssenKrupp AG is a major German multinational conglomerate specializing in industrial engineering and steel production, with significant operations in areas such as elevators, automotive components, and plant technology.
  • B. ArcelorMittal
    ArcelorMittal is a multinational steel manufacturing corporation and one of the world’s largest steel producers, headquartered in Luxembourg.
  • C. Mitsubishi Materials
    Mitsubishi Materials is a major Japanese manufacturer of materials and components, producing metals, cement, electronic materials, and advanced industrial products as part of the Mitsubishi corporate group.
  • D. International Steel Group
    International Steel Group was a major American steel company formed in the early 2000s that consolidated several bankrupt U.S. steel producers into a single, more competitive enterprise.
  • E. AK Steel Holding Corporation
    AK Steel Holding Corporation is a major American steel manufacturer known for producing flat-rolled carbon, stainless, and electrical steel products for automotive, appliance, construction, and other industrial markets.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ThyssenKrupp Materials Services
Target entity description: ThyssenKrupp Materials Services is the materials distribution and service arm of ThyssenKrupp AG, specializing in global supply, processing, and logistics for metals and industrial materials.
  • A. ThyssenKrupp AG chosen
    ThyssenKrupp AG is a major German multinational conglomerate specializing in industrial engineering and steel production, with significant operations in areas such as elevators, automotive components, and plant technology.
  • B. ArcelorMittal
    ArcelorMittal is a multinational steel manufacturing corporation and one of the world’s largest steel producers, headquartered in Luxembourg.
  • C. Mitsubishi Materials
    Mitsubishi Materials is a major Japanese manufacturer of materials and components, producing metals, cement, electronic materials, and advanced industrial products as part of the Mitsubishi corporate group.
  • D. International Steel Group
    International Steel Group was a major American steel company formed in the early 2000s that consolidated several bankrupt U.S. steel producers into a single, more competitive enterprise.
  • E. AK Steel Holding Corporation
    AK Steel Holding Corporation is a major American steel manufacturer known for producing flat-rolled carbon, stainless, and electrical steel products for automotive, appliance, construction, and other industrial markets.
  • F. None of above.

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_69d8e8dc5d8c8190a6d7bd8864f43ca0 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63d2f39188190976e8b6b111499a0 completed April 20, 2026, 2:50 p.m.
Created at: April 10, 2026, 1:41 p.m.