Triple

T18698537
Position Surface form Disambiguated ID Type / Status
Subject Emperor Wen of Sui E457184 entity
Predicate child P120 FINISHED
Object Yang Jun
Yang Jun was a prince of the Sui dynasty in China, known primarily as a son of Emperor Wen of Sui.
E1338967 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: Yang Jun | Statement: [Emperor Wen of Sui, child, Yang Jun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yang Jun
Context triple: [Emperor Wen of Sui, child, Yang Jun]
  • A. Yang Chen
    Yang Chen is a retired Chinese footballer best known as one of the first successful Chinese players in the German Bundesliga and a key forward for club and country in the late 1990s and early 2000s.
  • B. Wei Yunsong
    Wei Yunsong was a Chinese military and political leader associated with the regional Guangxi warlord faction during the Republican era.
  • C. Yang Ye
    Yang Ye was a famed Song dynasty military general and folk hero of the Yang clan, celebrated in Chinese history and legend for his loyalty and battlefield prowess.
  • D. Feng Jicai
    Feng Jicai is a prominent Chinese writer, cultural scholar, and preservationist known for his fiction and his efforts to protect China's urban and folk cultural heritage.
  • E. Yang Lun
    Yang Lun is a Chinese cinematographer best known for his work on the acclaimed film "Raise the Red Lantern."
  • 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: Yang Jun
Triple: [Emperor Wen of Sui, child, Yang Jun]
Generated description
Yang Jun was a prince of the Sui dynasty in China, known primarily as a son of Emperor Wen of Sui.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Yang Jun
Target entity description: Yang Jun was a prince of the Sui dynasty in China, known primarily as a son of Emperor Wen of Sui.
  • A. Yang Chen
    Yang Chen is a retired Chinese footballer best known as one of the first successful Chinese players in the German Bundesliga and a key forward for club and country in the late 1990s and early 2000s.
  • B. Wei Yunsong
    Wei Yunsong was a Chinese military and political leader associated with the regional Guangxi warlord faction during the Republican era.
  • C. Yang Ye
    Yang Ye was a famed Song dynasty military general and folk hero of the Yang clan, celebrated in Chinese history and legend for his loyalty and battlefield prowess.
  • D. Feng Jicai
    Feng Jicai is a prominent Chinese writer, cultural scholar, and preservationist known for his fiction and his efforts to protect China's urban and folk cultural heritage.
  • E. Yang Lun
    Yang Lun is a Chinese cinematographer best known for his work on the acclaimed film "Raise the Red Lantern."
  • 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_69d8d392aad081909fe31aa03e6e97d1 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e562e984988190ae902d41edd8faff completed April 19, 2026, 11:19 p.m.
NED1 Entity disambiguation (via context triple) batch_6a052b34a8108190a612e5334efb123c completed May 14, 2026, 1:53 a.m.
NEDg Description generation batch_6a052cf643b48190b40115e6e3b8cb81 completed May 14, 2026, 2:01 a.m.
NED2 Entity disambiguation (via description) batch_6a052e457dac8190a1160def70faad6e completed May 14, 2026, 2:07 a.m.
Created at: April 10, 2026, 11:49 a.m.