Triple

T9944179
Position Surface form Disambiguated ID Type / Status
Subject Sun Liang E194160 entity
Predicate regent P6804 FINISHED
Object Sun Jun
Sun Jun was a powerful Eastern Wu statesman and military figure of the Three Kingdoms period who effectively controlled the government as regent before his early death.
 E830345 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: Sun Jun | Statement: [Sun Liang, regent, Sun Jun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sun Jun
Context triple: [Sun Liang, regent, Sun Jun]
  • A. Sun
    Sun I-hsien is a Taiwanese politician who has served in various governmental roles, including as a legislator.
  • B. Sun
    The Sun is the massive, luminous star at the center of our solar system that provides the light and heat necessary for life on Earth.
  • C. Injune
    Injune is a small rural town in Queensland, Australia, known as a service centre for the surrounding agricultural and resource-producing region.
  • D. SUN
    SUN is the Australian Securities Exchange (ASX) ticker symbol for Suncorp Group, a major Australian finance, insurance, and banking corporation.
  • E. SUN
    SUN is the National Rail station code for Sunderland railway station in Tyne and Wear, England.
  • 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: Sun Jun
Triple: [Sun Liang, regent, Sun Jun]
Generated description
Sun Jun was a powerful Eastern Wu statesman and military figure of the Three Kingdoms period who effectively controlled the government as regent before his early death.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sun Jun
Target entity description: Sun Jun was a powerful Eastern Wu statesman and military figure of the Three Kingdoms period who effectively controlled the government as regent before his early death.
  • A. Sun
    Sun I-hsien is a Taiwanese politician who has served in various governmental roles, including as a legislator.
  • B. Sun
    The Sun is the massive, luminous star at the center of our solar system that provides the light and heat necessary for life on Earth.
  • C. Injune
    Injune is a small rural town in Queensland, Australia, known as a service centre for the surrounding agricultural and resource-producing region.
  • D. SUN
    SUN is the National Rail station code for Sunderland railway station in Tyne and Wear, England.
  • E. SUN
    SUN is the Australian Securities Exchange (ASX) ticker symbol for Suncorp Group, a major Australian finance, insurance, and banking corporation.
  • 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_69ca82e409348190a393777356b80a2a completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb613fbb48190b82a06987310cc96 completed April 2, 2026, 12:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2291a22f88190acf055a7410c1808 completed April 5, 2026, 9:19 a.m.
NEDg Description generation batch_69d229f496c48190bf3bca109b3bc62b completed April 5, 2026, 9:23 a.m.
NED2 Entity disambiguation (via description) batch_69d22a8494f481909bd6b4936b32679e completed April 5, 2026, 9:25 a.m.
Created at: March 30, 2026, 8:45 p.m.