Triple

T12210728
Position Surface form Disambiguated ID Type / Status
Subject Chu–Han Contention E290948 entity
Predicate hasLeader P981 FINISHED
Object Xiao He
Xiao He was a prominent early Han dynasty statesman and strategist who played a crucial role in Liu Bang’s rise to power and the establishment of the Han Empire.
 E971334 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: Xiao He | Statement: [Chu–Han Contention, hasLeader, Xiao He]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Xiao He
Context triple: [Chu–Han Contention, hasLeader, Xiao He]
  • A. He Ping
    He Ping is a Chinese political figure known primarily as the husband of Deng Rong, the daughter of former Chinese leader Deng Xiaoping.
  • B. Xiong Huai
    Xiong Huai was an ancient Chinese monarch who ruled the state of Chu during the Warring States period.
  • C. Wang He
    Wang He was a military commander of the State of Qin during the Warring States period of ancient China, known for his role in the campaigns surrounding the Battle of Changping.
  • D. Li Hai
    Li Hai is a Chinese human rights activist known for his pro-democracy efforts and imprisonment in China, for which he received international recognition.
  • E. Wu Shihuo
    Wu Shihuo was a Tang dynasty official and aristocrat best known as the father of China's only female emperor, Wu Zetian.
  • 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: Xiao He
Triple: [Chu–Han Contention, hasLeader, Xiao He]
Generated description
Xiao He was a prominent early Han dynasty statesman and strategist who played a crucial role in Liu Bang’s rise to power and the establishment of the Han Empire.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Xiao He
Target entity description: Xiao He was a prominent early Han dynasty statesman and strategist who played a crucial role in Liu Bang’s rise to power and the establishment of the Han Empire.
  • A. He Ping
    He Ping is a Chinese political figure known primarily as the husband of Deng Rong, the daughter of former Chinese leader Deng Xiaoping.
  • B. Xiong Huai
    Xiong Huai was an ancient Chinese monarch who ruled the state of Chu during the Warring States period.
  • C. Wang He
    Wang He was a military commander of the State of Qin during the Warring States period of ancient China, known for his role in the campaigns surrounding the Battle of Changping.
  • D. Li Hai
    Li Hai is a Chinese human rights activist known for his pro-democracy efforts and imprisonment in China, for which he received international recognition.
  • E. Wu Shihuo
    Wu Shihuo was a Tang dynasty official and aristocrat best known as the father of China's only female emperor, Wu Zetian.
  • 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_69d6ab65923081909acfc61b7a612233 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91c7ed4688190b0546b784e36b0ec completed April 10, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f60a9f45108190a814cdca52e77b5e completed May 2, 2026, 2:30 p.m.
NEDg Description generation batch_69f60bdbee288190991b08ae685bb401 completed May 2, 2026, 2:36 p.m.
NED2 Entity disambiguation (via description) batch_69f610ba7a608190b29f25ee2752ba7e completed May 2, 2026, 2:56 p.m.
Created at: April 8, 2026, 9:51 p.m.