Triple

T17748987
Position Surface form Disambiguated ID Type / Status
Subject Red Sorghum E443064 entity
Predicate editor P1954 FINISHED
Object Du Yuan
Du Yuan is a literary editor known for working on the acclaimed Chinese novel "Red Sorghum."
E1304815 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: Du Yuan | Statement: [Red Sorghum, editor, Du Yuan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Du Yuan
Context triple: [Red Sorghum, editor, Du Yuan]
  • A. Yuan Keding
    Yuan Keding was the eldest son of Chinese warlord and short-lived emperor Yuan Shikai, known mainly for his role within his father's regime during the early Republic of China.
  • B. Wu Yuan
    Wu Yuan, better known as Wu Zixu, was a famed statesman and military strategist of the Spring and Autumn period in ancient China, renowned for his role in the rise of the State of Wu.
  • C. Liu Jichi
    Liu Jichi was a Ming dynasty scholar-official known for helping compile the monumental Yongle Encyclopedia, one of the largest encyclopedic works in history.
  • D. Fu Sheng
    Fu Sheng was a short-lived and notoriously cruel emperor of the Former Qin state during China’s Sixteen Kingdoms period.
  • E. Zhu Houxi
    Zhu Houxi was a Ming dynasty imperial prince, known primarily as a son of the Hongzhi Emperor of China.
  • 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: Du Yuan
Triple: [Red Sorghum, editor, Du Yuan]
Generated description
Du Yuan is a literary editor known for working on the acclaimed Chinese novel "Red Sorghum."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Du Yuan
Target entity description: Du Yuan is a literary editor known for working on the acclaimed Chinese novel "Red Sorghum."
  • A. Yuan Keding
    Yuan Keding was the eldest son of Chinese warlord and short-lived emperor Yuan Shikai, known mainly for his role within his father's regime during the early Republic of China.
  • B. Wu Yuan
    Wu Yuan, better known as Wu Zixu, was a famed statesman and military strategist of the Spring and Autumn period in ancient China, renowned for his role in the rise of the State of Wu.
  • C. Liu Jichi
    Liu Jichi was a Ming dynasty scholar-official known for helping compile the monumental Yongle Encyclopedia, one of the largest encyclopedic works in history.
  • D. Fu Sheng
    Fu Sheng was a short-lived and notoriously cruel emperor of the Former Qin state during China’s Sixteen Kingdoms period.
  • E. Zhu Houxi
    Zhu Houxi was a Ming dynasty imperial prince, known primarily as a son of the Hongzhi Emperor of China.
  • 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e47ad46a50819089c87f74efe3c7ca completed April 19, 2026, 6:48 a.m.
NED1 Entity disambiguation (via context triple) batch_6a035d76eb3c81908d7b7a770a47f725 completed May 12, 2026, 5:03 p.m.
NEDg Description generation batch_6a03633013148190b597d2ee923131d9 completed May 12, 2026, 5:28 p.m.
NED2 Entity disambiguation (via description) batch_6a0363b88210819098837b6e08083ac0 completed May 12, 2026, 5:30 p.m.
Created at: April 10, 2026, 10:10 a.m.