Triple

T16380583
Position Surface form Disambiguated ID Type / Status
Subject Emperor Zhangzong of Jin E397794 entity
Predicate spouse P13 FINISHED
Object Empress Tudan
Empress Tudan was a consort of Emperor Zhangzong of the Jurchen-led Jin dynasty in China, holding the title of empress during his reign.
 E1209502 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: Empress Tudan | Statement: [Emperor Zhangzong of Jin, spouse, Empress Tudan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Empress Tudan
Context triple: [Emperor Zhangzong of Jin, spouse, Empress Tudan]
  • A. Empress Pan
    Empress Pan was the wife of Eastern Wu ruler Sun Quan and briefly served as empress during the Three Kingdoms period of China.
  • B. Empress
    Empress is a studio album by Nigerian singer Yemi Alade that showcases her Afro-pop sound and themes of female empowerment.
  • C. Empress
    Empress was the radio callsign used by Canadian Pacific Air Lines for its commercial flight operations.
  • D. Empress
    Empress is a science fiction comic book series written by Mark Millar that follows a queen fleeing a tyrannical galactic emperor with her children across the universe.
  • E. Empress
    Empress is the title given to the principal wife or female counterpart of an emperor, often serving as the highest-ranking woman in an imperial court.
  • 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: Empress Tudan
Triple: [Emperor Zhangzong of Jin, spouse, Empress Tudan]
Generated description
Empress Tudan was a consort of Emperor Zhangzong of the Jurchen-led Jin dynasty in China, holding the title of empress during his reign.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Empress Tudan
Target entity description: Empress Tudan was a consort of Emperor Zhangzong of the Jurchen-led Jin dynasty in China, holding the title of empress during his reign.
  • A. Empress Pan
    Empress Pan was the wife of Eastern Wu ruler Sun Quan and briefly served as empress during the Three Kingdoms period of China.
  • B. Empress
    Empress is a studio album by Nigerian singer Yemi Alade that showcases her Afro-pop sound and themes of female empowerment.
  • C. Empress
    Empress was the radio callsign used by Canadian Pacific Air Lines for its commercial flight operations.
  • D. Empress
    Empress is a science fiction comic book series written by Mark Millar that follows a queen fleeing a tyrannical galactic emperor with her children across the universe.
  • E. Empress
    Empress is the title given to the principal wife or female counterpart of an emperor, often serving as the highest-ranking woman in an imperial court.
  • 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_69d87f2880b48190ae1a9673a3bbef80 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e319db5b648190a8fca23518a1fb39 completed April 18, 2026, 5:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0035689ef08190ba980a359498ca56 completed May 10, 2026, 7:36 a.m.
NEDg Description generation batch_6a00363c50848190a6a3d692cbe07cd0 completed May 10, 2026, 7:39 a.m.
NED2 Entity disambiguation (via description) batch_6a0036e53f2c81908f04a5e51870040c completed May 10, 2026, 7:42 a.m.
Created at: April 10, 2026, 5:08 a.m.