Triple

T1008902
Position Surface form Disambiguated ID Type / Status
Subject Steve Wozniak E21775 entity
Predicate founded P104 FINISHED
Object CL 9
CL 9 is a technology company co-founded by Apple co-founder Steve Wozniak, focused on cloud computing and data center services.
 E122381 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: CL 9 | Statement: [Steve Wozniak, founded, CL 9]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CL 9
Context triple: [Steve Wozniak, founded, CL 9]
  • A. CL
    CL is the common abbreviation for Japan’s professional baseball Central League.
  • B. CLCS
    CLCS is a United Nations body of experts that evaluates and makes recommendations on coastal states’ claims to the outer limits of their continental shelves under the UN Convention on the Law of the Sea.
  • C. CLP
    CLP is the three-letter ISO 4217 currency code for the Chilean peso, the official monetary unit of Chile.
  • D. CLU
    CLU is an early high-level programming language from the 1970s that pioneered data abstraction, iterators, and exception handling, significantly influencing the design of later languages.
  • E. CLS
    The Mercedes-Benz CLS is a luxury four-door coupé known for pioneering the modern coupé-sedan design with sleek styling and high-end performance.
  • 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: CL 9
Triple: [Steve Wozniak, founded, CL 9]
Generated description
CL 9 is a technology company co-founded by Apple co-founder Steve Wozniak, focused on cloud computing and data center services.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CL 9
Target entity description: CL 9 is a technology company co-founded by Apple co-founder Steve Wozniak, focused on cloud computing and data center services.
  • A. CL
    CL is the common abbreviation for Japan’s professional baseball Central League.
  • B. CLCS
    CLCS is a United Nations body of experts that evaluates and makes recommendations on coastal states’ claims to the outer limits of their continental shelves under the UN Convention on the Law of the Sea.
  • C. CLP
    CLP is the three-letter ISO 4217 currency code for the Chilean peso, the official monetary unit of Chile.
  • D. CLU
    CLU is an early high-level programming language from the 1970s that pioneered data abstraction, iterators, and exception handling, significantly influencing the design of later languages.
  • E. CLS
    The Mercedes-Benz CLS is a luxury four-door coupé known for pioneering the modern coupé-sedan design with sleek styling and high-end performance.
  • 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_69a493c53e648190ae8cb76c433fd9a7 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b7a2186c819081a495bc15f8c7fd completed March 1, 2026, 10:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac3ba9406c81909a13375fea05ee99 completed March 7, 2026, 2:52 p.m.
NEDg Description generation batch_69ac3c0491788190b6a1f6d80c4b26ce completed March 7, 2026, 2:53 p.m.
NED2 Entity disambiguation (via description) batch_69ac3cbb30d081909759df25c21eb275 completed March 7, 2026, 2:56 p.m.
Created at: March 1, 2026, 7:41 p.m.