Triple

T5983393
Position Surface form Disambiguated ID Type / Status
Subject Naxi language E133170 entity
Predicate notableResearcher P22 FINISHED
Object Fang Guoyu
Fang Guoyu was a prominent Chinese scholar known for his pioneering research and documentation of the Naxi language and Dongba culture.
E584031 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: Fang Guoyu | Statement: [Naxi language, notableResearcher, Fang Guoyu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fang Guoyu
Context triple: [Naxi language, notableResearcher, Fang Guoyu]
  • A. Guan Qihui
    Guan Qihui is a Chinese sculptor best known for designing the iconic Five Rams Statue in Guangzhou.
  • B. Gao Junman
    Gao Junman was the wife of Chinese revolutionary and intellectual Chen Duxiu, associated with the early Chinese Communist movement.
  • C. Zhang Fakui
    Zhang Fakui was a prominent Nationalist Chinese general who played key roles in major early battles of the Second Sino-Japanese War.
  • D. Wan Fulin
    Wan Fulin was a prominent Chinese warlord and military commander from Northeast China who played a significant role in regional politics and resistance against Japanese aggression during the Republican era.
  • E. Guo Boxiong
    Guo Boxiong is a former high-ranking Chinese general and vice chairman of the Central Military Commission who was later convicted of corruption.
  • 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: Fang Guoyu
Triple: [Naxi language, notableResearcher, Fang Guoyu]
Generated description
Fang Guoyu was a prominent Chinese scholar known for his pioneering research and documentation of the Naxi language and Dongba culture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Fang Guoyu
Target entity description: Fang Guoyu was a prominent Chinese scholar known for his pioneering research and documentation of the Naxi language and Dongba culture.
  • A. Guan Qihui
    Guan Qihui is a Chinese sculptor best known for designing the iconic Five Rams Statue in Guangzhou.
  • B. Gao Junman
    Gao Junman was the wife of Chinese revolutionary and intellectual Chen Duxiu, associated with the early Chinese Communist movement.
  • C. Zhang Fakui
    Zhang Fakui was a prominent Nationalist Chinese general who played key roles in major early battles of the Second Sino-Japanese War.
  • D. Wan Fulin
    Wan Fulin was a prominent Chinese warlord and military commander from Northeast China who played a significant role in regional politics and resistance against Japanese aggression during the Republican era.
  • E. Guo Boxiong
    Guo Boxiong is a former high-ranking Chinese general and vice chairman of the Central Military Commission who was later convicted of corruption.
  • 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_69c0086f45e8819098f73dd16d45ec9d completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04a6a9f2c8190b900cd7e3ab9fe42 completed March 22, 2026, 8 p.m.
NED1 Entity disambiguation (via context triple) batch_69c5e3a5d54c8190b2bc8b3291f8ac2f completed March 27, 2026, 1:55 a.m.
NEDg Description generation batch_69c5ea0b6fc48190873a9db630f78f24 completed March 27, 2026, 2:23 a.m.
NED2 Entity disambiguation (via description) batch_69c5ea9f8b0081908f950d490c3098de completed March 27, 2026, 2:25 a.m.
Created at: March 22, 2026, 4:04 p.m.