Triple

T15087738
Position Surface form Disambiguated ID Type / Status
Subject Zhu Changxun E360323 entity
Predicate mother P120 FINISHED
Object Consort Zheng
Consort Zheng was a favored imperial consort of the Ming dynasty whose son Zhu Changxun became a prominent prince.
E1136960 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: Consort Zheng | Statement: [Zhu Changxun, mother, Consort Zheng]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Consort Zheng
Context triple: [Zhu Changxun, mother, Consort Zheng]
  • A. Consort Wang
    Consort Wang was an imperial consort of the Ming dynasty’s last ruler, the Chongzhen Emperor, known primarily for her role in the final years of the collapsing dynasty.
  • B. Consort Wang
    Consort Wang was an imperial consort of the Tang dynasty best known as the mother of Emperor Xianzong.
  • C. Consort Jia
    Consort Jia was an imperial consort of the Eastern Han dynasty best known as the mother of Emperor Zhang of Han.
  • D. Consort Guo
    Consort Guo was an imperial consort of Cao Rui, the second emperor of the state of Cao Wei during China’s Three Kingdoms period.
  • E. Consort Guo
    Consort Guo was an imperial consort of the late Tang dynasty best known as the mother of Emperor Xizong of Tang.
  • 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: Consort Zheng
Triple: [Zhu Changxun, mother, Consort Zheng]
Generated description
Consort Zheng was a favored imperial consort of the Ming dynasty whose son Zhu Changxun became a prominent prince.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Consort Zheng
Target entity description: Consort Zheng was a favored imperial consort of the Ming dynasty whose son Zhu Changxun became a prominent prince.
  • A. Consort Wang
    Consort Wang was an imperial consort of the Ming dynasty’s last ruler, the Chongzhen Emperor, known primarily for her role in the final years of the collapsing dynasty.
  • B. Consort Wang
    Consort Wang was an imperial consort of the Tang dynasty best known as the mother of Emperor Xianzong.
  • C. Consort Jia
    Consort Jia was an imperial consort of the Eastern Han dynasty best known as the mother of Emperor Zhang of Han.
  • D. Consort Guo
    Consort Guo was an imperial consort of Cao Rui, the second emperor of the state of Cao Wei during China’s Three Kingdoms period.
  • E. Consort Guo
    Consort Guo was an imperial consort of the late Tang dynasty best known as the mother of Emperor Xizong of Tang.
  • 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_69d85a035aa88190b52a139d3a1b7b6d completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e00276d1608190bc310d5b86ecd1d5 completed April 15, 2026, 9:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69feae1ba4208190b1e8c55668a1b422 completed May 9, 2026, 3:46 a.m.
NEDg Description generation batch_69feb10161fc81908aef193552ada55b completed May 9, 2026, 3:58 a.m.
NED2 Entity disambiguation (via description) batch_69feb168eac0819098bd76bac6daa838 completed May 9, 2026, 4 a.m.
Created at: April 10, 2026, 3:03 a.m.