Triple

T8531021
Position Surface form Disambiguated ID Type / Status
Subject State of Wei E201948 entity
Predicate pinyinName P9333 FINISHED
Object Wèi
Wèi is the pinyin romanization of the name of the ancient Chinese State of Wei, a major political power during the Warring States period.
 E741767 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: Wèi | Statement: [State of Wei, pinyinName, Wèi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Wèi
Context triple: [State of Wei, pinyinName, Wèi]
  • A. Wen
    Wen is the given name of Sun I-hsien, a person identifiable by this personal name within Chinese naming conventions.
  • B. Vengi
    Vengi was an important early medieval city and region in southeastern India that served as a major political and cultural center under the Eastern Chalukya dynasty.
  • C. Wojin
    Wojin is a family surname associated with individuals such as Benji Wojin.
  • D. Gweru
    Gweru is a central Zimbabwean city that serves as the capital of the Midlands Province and an important commercial and transportation hub.
  • E. Wonsal
    Wonsal is the original family surname of Harry Warner, one of the founding brothers of Warner Bros. film studio.
  • 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: Wèi
Triple: [State of Wei, pinyinName, Wèi]
Generated description
Wèi is the pinyin romanization of the name of the ancient Chinese State of Wei, a major political power during the Warring States period.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Wèi
Target entity description: Wèi is the pinyin romanization of the name of the ancient Chinese State of Wei, a major political power during the Warring States period.
  • A. Wen
    Wen is the given name of Sun I-hsien, a person identifiable by this personal name within Chinese naming conventions.
  • B. Vengi
    Vengi was an important early medieval city and region in southeastern India that served as a major political and cultural center under the Eastern Chalukya dynasty.
  • C. Wojin
    Wojin is a family surname associated with individuals such as Benji Wojin.
  • D. Gweru
    Gweru is a central Zimbabwean city that serves as the capital of the Midlands Province and an important commercial and transportation hub.
  • E. Wonsal
    Wonsal is the original family surname of Harry Warner, one of the founding brothers of Warner Bros. film studio.
  • 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_69ca83228b24819085d22e7dc99f5d94 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe67546248190b359c845c0161ad3 completed March 31, 2026, 3:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce6d68d14c81908bde8ca0113f9503 completed April 2, 2026, 1:21 p.m.
NEDg Description generation batch_69ce6ec1e74081908fc235ffd13ef301 completed April 2, 2026, 1:27 p.m.
NED2 Entity disambiguation (via description) batch_69ce6fe13a00819095f5bec408435426 completed April 2, 2026, 1:32 p.m.
Created at: March 30, 2026, 6:17 p.m.