Triple

T20738973
Position Surface form Disambiguated ID Type / Status
Subject Sharon Case E509787 entity
Predicate employer P7 FINISHED
Object CBS
CBS is a major American television and radio broadcasting network known for its wide range of news, sports, and entertainment programming.
E6070 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: CBS | Statement: [Sharon Case, employer, CBS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CBS
Context triple: [Sharon Case, employer, CBS]
  • A. CBS
    CBS is a leading Danish university in Copenhagen specializing in business and economics education and research.
  • B. CBS
    CBS is the commonly used abbreviation for the Commission for Basic Systems, a specialized body focused on foundational infrastructure and standards, likely within an international or governmental organizational context.
  • C. CBS
    CBS is the acronym for the Central Bank of Somalia, the country’s primary monetary authority responsible for issuing currency and overseeing financial stability.
  • D. CBS
    CBS is the Curtin Business School, a leading Australian institution offering business education and research as part of Curtin University.
  • E. CBS
    CBS is a premier undergraduate college of the University of Delhi specializing in business, management, and computer science education.
  • 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: CBS
Triple: [Sharon Case, employer, CBS]
Generated description
CBS is a major American television and radio broadcasting network known for its wide range of news, sports, and entertainment programming.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: CBS
Target entity description: CBS is a major American television and radio broadcasting network known for its wide range of news, sports, and entertainment programming.
  • A. CBS chosen
    CBS is a major American broadcast television network known for airing a wide range of popular news, sports, and entertainment programming nationwide.
  • B. CBS
    CBS is a leading graduate business school of Columbia University in New York City, renowned for its MBA and finance programs.
  • C. CBS
    CBS is the national statistical office of the Netherlands responsible for collecting, analyzing, and publishing data on the country’s economy, population, and society.
  • D. CBS
    CBS is the commonly used abbreviation for the Commission for Basic Systems, a specialized body focused on foundational infrastructure and standards, likely within an international or governmental organizational context.
  • E. CBS
    CBS is a Harvard University research center dedicated to advancing the understanding of the brain through interdisciplinary neuroscience studies.
  • F. None of above.

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_69e0b4c589c08190834fb5d86d0efa2b completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c20c36708190898b889b6989fc7d completed April 21, 2026, 12:17 a.m.
NED1 Entity disambiguation (via context triple) batch_6a08ef79f3cc81908e5bd0d88a49af37 completed May 16, 2026, 10:28 p.m.
NEDg Description generation batch_6a08f1c8a1b08190b8d0f3e84a195ef5 completed May 16, 2026, 10:38 p.m.
NED2 Entity disambiguation (via description) batch_6a08f22a69348190869d69ec6144f85e completed May 16, 2026, 10:39 p.m.
Created at: April 16, 2026, 12:32 p.m.