Triple

T9171693
Position Surface form Disambiguated ID Type / Status
Subject Emperor Suzong of Tang E220094 entity
Predicate opponent P437 FINISHED
Object An Lushan
An Lushan was a Tang dynasty general of Sogdian and Turkic origin who led the devastating An Lushan Rebellion (755–763), which severely weakened the Tang Empire.
 E782721 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: An Lushan | Statement: [Emperor Suzong of Tang, opponent, An Lushan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: An Lushan
Context triple: [Emperor Suzong of Tang, opponent, An Lushan]
  • A. Mount Wangwu
    Mount Wangwu is a renowned scenic mountain area in China, celebrated for its dramatic landscapes, cultural legends, and historical significance within the Taihang mountain range.
  • B. Tudigong
    Tudigong is a widely venerated Chinese earth god and local tutelary deity associated with protecting land, villages, and community welfare.
  • C. Ma Sichun
    Ma Sichun is a Chinese actress known for her acclaimed film and television roles, including winning the Golden Horse Award for Best Leading Actress.
  • D. Taishi
    Taishi is a town in Osaka Prefecture, Japan, known for its historical sites and traditional rural character.
  • E. Mao Ling
    Mao Ling is the mausoleum complex that serves as the imperial tomb of the Ming dynasty Chenghua Emperor in 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: An Lushan
Triple: [Emperor Suzong of Tang, opponent, An Lushan]
Generated description
An Lushan was a Tang dynasty general of Sogdian and Turkic origin who led the devastating An Lushan Rebellion (755–763), which severely weakened the Tang Empire.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: An Lushan
Target entity description: An Lushan was a Tang dynasty general of Sogdian and Turkic origin who led the devastating An Lushan Rebellion (755–763), which severely weakened the Tang Empire.
  • A. Mount Wangwu
    Mount Wangwu is a renowned scenic mountain area in China, celebrated for its dramatic landscapes, cultural legends, and historical significance within the Taihang mountain range.
  • B. Tudigong
    Tudigong is a widely venerated Chinese earth god and local tutelary deity associated with protecting land, villages, and community welfare.
  • C. Ma Sichun
    Ma Sichun is a Chinese actress known for her acclaimed film and television roles, including winning the Golden Horse Award for Best Leading Actress.
  • D. Taishi
    Taishi is a town in Osaka Prefecture, Japan, known for its historical sites and traditional rural character.
  • E. Mao Ling
    Mao Ling is the mausoleum complex that serves as the imperial tomb of the Ming dynasty Chenghua Emperor in 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_69ca83e467108190abcae6a33b3d4dad completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccaae38ee48190bf783477bc37913d completed April 1, 2026, 5:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0549746b0819099c2a591900f9c8c completed April 4, 2026, midnight
NEDg Description generation batch_69d0558aeb7c8190a638e81bd0a6b47a completed April 4, 2026, 12:04 a.m.
NED2 Entity disambiguation (via description) batch_69d0598de6388190a535748893dfb09c completed April 4, 2026, 12:21 a.m.
Created at: March 30, 2026, 7:22 p.m.