Triple

T21943274
Position Surface form Disambiguated ID Type / Status
Subject Bernhard Karlgren E541873 entity
Predicate fieldOfWork P3 FINISHED
Object Chinese linguistics 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: Chinese linguistics | Statement: [Bernhard Karlgren, fieldOfWork, Chinese linguistics]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Chinese linguistics
Context triple: [Bernhard Karlgren, fieldOfWork, Chinese linguistics]
  • A. Chinese language
    The Chinese language is a family of related Sinitic languages and dialects, including Mandarin, Cantonese, and others, spoken by over a billion people primarily in China and across Chinese-speaking communities worldwide.
  • B. Mandarin phonology
    Mandarin phonology is the sound system of Standard Chinese, encompassing its consonants, vowels, tones, and syllable structure.
  • C. Chin language
    Chin language refers to a group of closely related Tibeto-Burman languages spoken primarily in Chin State of western Myanmar and adjacent regions of India and Bangladesh.
  • D. Chomskyan linguistics
    Chomskyan linguistics is a theoretical approach to language pioneered by Noam Chomsky that emphasizes humans’ innate linguistic capacity and focuses on the formal, generative rules underlying all natural languages.
  • E. Austronesian linguistics
    Austronesian linguistics is the branch of linguistics that studies the structure, history, and classification of the Austronesian language family, one of the world’s largest and most geographically widespread language groups.
  • 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: Chinese linguistics
Target entity description: Chinese linguistics is the scientific study of the Chinese language and its varieties, including their sounds, grammar, history, and writing systems.
  • A. Chinese language chosen
    The Chinese language is a family of related Sinitic languages and dialects, including Mandarin, Cantonese, and others, spoken by over a billion people primarily in China and across Chinese-speaking communities worldwide.
  • B. Mandarin phonology
    Mandarin phonology is the sound system of Standard Chinese, encompassing its consonants, vowels, tones, and syllable structure.
  • C. Chin language
    Chin language refers to a group of closely related Tibeto-Burman languages spoken primarily in Chin State of western Myanmar and adjacent regions of India and Bangladesh.
  • D. Chomskyan linguistics
    Chomskyan linguistics is a theoretical approach to language pioneered by Noam Chomsky that emphasizes humans’ innate linguistic capacity and focuses on the formal, generative rules underlying all natural languages.
  • E. Austronesian linguistics
    Austronesian linguistics is the branch of linguistics that studies the structure, history, and classification of the Austronesian language family, one of the world’s largest and most geographically widespread language groups.
  • 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_69e0c47e2e5c81909a7f74ce3de50911 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1242515ec8190b015bf8c7b13be85 completed April 28, 2026, 9:18 p.m.
Created at: April 16, 2026, 7:56 p.m.