Triple

T21101019
Position Surface form Disambiguated ID Type / Status
Subject Wei E519903 entity
Predicate hasVariantInTraditionalChinese P35394 FINISHED
Object 韋
韋 is a traditional Chinese character commonly used as a surname and as a radical associated with leather or tanned hide in Chinese writing.
 E1466113 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: 韋 | Statement: [Wei, hasVariantInTraditionalChinese, 韋]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: 韋
Context triple: [Wei, hasVariantInTraditionalChinese, 韋]
  • A. 鄭
    鄭 is a common Korean family name of Chinese origin, typically romanized as Jeong, Jung, or Chung.
  • B. 吳
    吳 is the Chinese name of the ancient State of Wu, a prominent kingdom during the Spring and Autumn period of Chinese history.
  • C. Wu
    Wu is a common Chinese surname borne by many notable individuals across politics, academia, entertainment, and sports.
  • D. 聂
    聂 is a Chinese surname commonly used in mainland China, associated with various historical and contemporary figures.
  • E. 陳
    陳 is a common Chinese surname and character with historical roots, widely used across Chinese-speaking communities and often romanized as "Chan," "Chen," or similar variants.
  • 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: 韋
Triple: [Wei, hasVariantInTraditionalChinese, 韋]
Generated description
韋 is a traditional Chinese character commonly used as a surname and as a radical associated with leather or tanned hide in Chinese writing.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: 韋
Target entity description: 韋 is a traditional Chinese character commonly used as a surname and as a radical associated with leather or tanned hide in Chinese writing.
  • A. 鄭
    鄭 is a common Korean family name of Chinese origin, typically romanized as Jeong, Jung, or Chung.
  • B. 吳
    吳 is the Chinese name of the ancient State of Wu, a prominent kingdom during the Spring and Autumn period of Chinese history.
  • C. Wu
    Wu is a common Chinese surname borne by many notable individuals across politics, academia, entertainment, and sports.
  • D. 聂
    聂 is a Chinese surname commonly used in mainland China, associated with various historical and contemporary figures.
  • E. 陳
    陳 is a common Chinese surname and character with historical roots, widely used across Chinese-speaking communities and often romanized as "Chan," "Chen," or similar variants.
  • 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_69e0b508d8dc81909be940dafe36c8f7 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e71b5e16cc81908257ccf8c9a59117 completed April 21, 2026, 6:38 a.m.
NED1 Entity disambiguation (via context triple) batch_6a095a62bd0c8190b10e3b472ba7e330 completed May 17, 2026, 6:04 a.m.
NEDg Description generation batch_6a095c9f10248190b4eab0842c6943f1 completed May 17, 2026, 6:13 a.m.
NED2 Entity disambiguation (via description) batch_6a095d6457608190904688689ec8982e completed May 17, 2026, 6:17 a.m.
Created at: April 16, 2026, 2:53 p.m.