Triple

T5973377
Position Surface form Disambiguated ID Type / Status
Subject Deutscher Aktienindex E132926 entity
Predicate sectorClassificationStandard P6736 FINISHED
Object Industry Classification Benchmark E195032 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: Industry Classification Benchmark | Statement: [Deutscher Aktienindex, sectorClassificationStandard, Industry Classification Benchmark]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Industry Classification Benchmark
Context triple: [Deutscher Aktienindex, sectorClassificationStandard, Industry Classification Benchmark]
  • A. Industry Classification Benchmark chosen
    The Industry Classification Benchmark is a globally used system that categorizes companies and securities into sectors and industries to facilitate investment analysis and benchmarking.
  • B. International Standard Industrial Classification
    The International Standard Industrial Classification is a globally used United Nations framework that systematically categorizes economic activities to enable consistent collection, analysis, and comparison of industrial statistics across countries.
  • C. NAICS codes
    NAICS codes are a standardized classification system used in North America to categorize businesses and industries for statistical, regulatory, and procurement purposes.
  • D. Bliss Classification, 2nd edition
    Bliss Classification, 2nd edition is a fully revised and expanded version of Henry E. Bliss’s bibliographic classification system, used in libraries to organize knowledge across all subject areas.
  • E. Classification Research Group
    The Classification Research Group was a mid-20th-century British collective of information scientists and librarians known for pioneering work in faceted classification and modern information organization theory.
  • 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_69c0086deab081908550159ca23eec9b completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04a01dd4081909097342afff31f9b completed March 22, 2026, 7:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0e40fa2488190b82d604d51b73090 completed March 23, 2026, 6:56 a.m.
Created at: March 22, 2026, 4:03 p.m.