Triple

T1645273
Position Surface form Disambiguated ID Type / Status
Subject Song dynasty E35566 entity
Predicate notablePerson P304 FINISHED
Object Sima Guang
Sima Guang was an influential Song dynasty historian and statesman best known for compiling the monumental historical chronicle "Zizhi Tongjian."
E187546 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: Sima Guang | Statement: [Song dynasty, notablePerson, Sima Guang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sima Guang
Context triple: [Song dynasty, notablePerson, Sima Guang]
  • A. Song Zheyuan
    Song Zheyuan was a Chinese Nationalist general best known for leading forces in North China during the early stages of the Second Sino-Japanese War.
  • B. He Zizhen
    He Zizhen was a Chinese revolutionary and early Communist Party member best known as one of Mao Zedong’s wives and a participant in the Long March.
  • C. Shan Zuchang
    Shan Zuchang is a Chinese businessman best known for serving as chairman of English football club West Bromwich Albion.
  • D. Kun Huang
    Kun Huang was a prominent Chinese physicist and crystallographer known for his influential work in solid-state physics and lattice dynamics.
  • E. Wang Jian
    Wang Jian was a prominent Qin dynasty general whose military campaigns were crucial in the unification of China under Qin rule.
  • 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: Sima Guang
Triple: [Song dynasty, notablePerson, Sima Guang]
Generated description
Sima Guang was an influential Song dynasty historian and statesman best known for compiling the monumental historical chronicle "Zizhi Tongjian."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sima Guang
Target entity description: Sima Guang was an influential Song dynasty historian and statesman best known for compiling the monumental historical chronicle "Zizhi Tongjian."
  • A. Song Zheyuan
    Song Zheyuan was a Chinese Nationalist general best known for leading forces in North China during the early stages of the Second Sino-Japanese War.
  • B. He Zizhen
    He Zizhen was a Chinese revolutionary and early Communist Party member best known as one of Mao Zedong’s wives and a participant in the Long March.
  • C. Shan Zuchang
    Shan Zuchang is a Chinese businessman best known for serving as chairman of English football club West Bromwich Albion.
  • D. Kun Huang
    Kun Huang was a prominent Chinese physicist and crystallographer known for his influential work in solid-state physics and lattice dynamics.
  • E. Wang Jian
    Wang Jian was a prominent Qin dynasty general whose military campaigns were crucial in the unification of China under Qin rule.
  • 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_69a88604618c81908b41f6429c431eb6 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a90a41e5a08190b97dd1c0b12c662a completed March 5, 2026, 4:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad6818c8288190af5307384f1c8080 completed March 8, 2026, 12:14 p.m.
NEDg Description generation batch_69ad68edbd2c819090c6556966eb279a completed March 8, 2026, 12:17 p.m.
NED2 Entity disambiguation (via description) batch_69ad69724c9c8190a2314a8f30f18f7d completed March 8, 2026, 12:20 p.m.
Created at: March 4, 2026, 7:28 p.m.