Triple

T185096
Position Surface form Disambiguated ID Type / Status
Subject AEX index E3962 entity
Predicate isComparableTo P278 FINISHED
Object BEL 20
The BEL 20 is the benchmark stock market index of Euronext Brussels, comprising the largest and most actively traded companies in Belgium.
 E23524 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: BEL 20 | Statement: [AEX index, isComparableTo, BEL 20]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BEL 20
Context triple: [AEX index, isComparableTo, BEL 20]
  • A. BEL
    BEL is the three-letter ISO 3166-1 alpha-3 country code that uniquely identifies Belgium in international standards and data systems.
  • B. BEP
    BEP is a United States government agency responsible for designing and producing paper currency and other secure documents.
  • C. BEA
    BEA is a U.S. government agency that produces key economic statistics, including measures of national income, output, and growth.
  • D. BOA
    BOA is the abbreviation commonly used for the British Olympic Association, the National Olympic Committee responsible for Great Britain and Northern Ireland’s participation in the Olympic Games.
  • E. BE
    BE is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Belgium in international standards and systems.
  • 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: BEL 20
Triple: [AEX index, isComparableTo, BEL 20]
Generated description
The BEL 20 is the benchmark stock market index of Euronext Brussels, comprising the largest and most actively traded companies in Belgium.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BEL 20
Target entity description: The BEL 20 is the benchmark stock market index of Euronext Brussels, comprising the largest and most actively traded companies in Belgium.
  • A. BEL
    BEL is the three-letter ISO 3166-1 alpha-3 country code that uniquely identifies Belgium in international standards and data systems.
  • B. BEP
    BEP is a United States government agency responsible for designing and producing paper currency and other secure documents.
  • C. BEA
    BEA is a U.S. government agency that produces key economic statistics, including measures of national income, output, and growth.
  • D. BOA
    BOA is the abbreviation commonly used for the British Olympic Association, the National Olympic Committee responsible for Great Britain and Northern Ireland’s participation in the Olympic Games.
  • E. BE
    BE is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Belgium in international standards and systems.
  • 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_69a25497e2f08190a040f8c6e1842643 completed Feb. 28, 2026, 2:36 a.m.
NER Named-entity recognition batch_69a25bc834388190a93ec1ab0d5946de completed Feb. 28, 2026, 3:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2fd0577588190a91be504e3c9f0ab completed Feb. 28, 2026, 2:34 p.m.
NEDg Description generation batch_69a2fe0b1c148190854569c3f6e03a91 completed Feb. 28, 2026, 2:39 p.m.
NED2 Entity disambiguation (via description) batch_69a2fe7676488190b0d126a7d3d75b5f completed Feb. 28, 2026, 2:40 p.m.
Created at: Feb. 28, 2026, 2:40 a.m.