Triple

T9918525
Position Surface form Disambiguated ID Type / Status
Subject Emperor Wu of Han E185930 entity
Predicate child P120 FINISHED
Object Liu Dan
Liu Dan was a Han dynasty imperial prince, best known as the son of Emperor Wu of Han.
 E830512 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: Liu Dan | Statement: [Emperor Wu of Han, child, Liu Dan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Liu Dan
Context triple: [Emperor Wu of Han, child, Liu Dan]
  • A. Liu Dong
    Liu Dong is a Chinese middle-distance runner best known for winning the women's 1500 metres world title in 1993 as part of coach Ma Junren's famed "Ma's Army."
  • B. Jiang Wenli
    Jiang Wenli is a renowned Chinese actress celebrated for her versatile performances in film and television dramas.
  • C. Ye Li
    Ye Li is a retired Chinese women's basketball player best known as the wife of former NBA star Yao Ming.
  • D. Qu Dongyu
    Qu Dongyu is a Chinese agronomist and politician who serves as the Director-General of the United Nations Food and Agriculture Organization, leading global efforts to combat hunger and promote sustainable agriculture.
  • E. Liu Qin
    Liu Qin was a prince of the Eastern Han dynasty, known primarily as a son of Emperor Guangwu of Han.
  • 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: Liu Dan
Triple: [Emperor Wu of Han, child, Liu Dan]
Generated description
Liu Dan was a Han dynasty imperial prince, best known as the son of Emperor Wu of Han.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Liu Dan
Target entity description: Liu Dan was a Han dynasty imperial prince, best known as the son of Emperor Wu of Han.
  • A. Liu Dong
    Liu Dong is a Chinese middle-distance runner best known for winning the women's 1500 metres world title in 1993 as part of coach Ma Junren's famed "Ma's Army."
  • B. Jiang Wenli
    Jiang Wenli is a renowned Chinese actress celebrated for her versatile performances in film and television dramas.
  • C. Ye Li
    Ye Li is a retired Chinese women's basketball player best known as the wife of former NBA star Yao Ming.
  • D. Qu Dongyu
    Qu Dongyu is a Chinese agronomist and politician who serves as the Director-General of the United Nations Food and Agriculture Organization, leading global efforts to combat hunger and promote sustainable agriculture.
  • E. Liu Qin
    Liu Qin was a prince of the Eastern Han dynasty, known primarily as a son of Emperor Guangwu of Han.
  • 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_69ca829b45f481909040f7b99a1976ed completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cdb5685a908190ab3e55b9bf9613f6 completed April 2, 2026, 12:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69d228b8974c81909a603407ebe3df1f completed April 5, 2026, 9:17 a.m.
NEDg Description generation batch_69d22990ef5881908b6a6100d7dcf6e6 completed April 5, 2026, 9:21 a.m.
NED2 Entity disambiguation (via description) batch_69d22a0cb0808190a6119dc0268c50b9 completed April 5, 2026, 9:23 a.m.
Created at: March 30, 2026, 8:42 p.m.