Triple

T4307803
Position Surface form Disambiguated ID Type / Status
Subject Mao Zedong family E93997 entity
Predicate hasChildOfPatriarch P6882 FINISHED
Object Mao Anhong E442798 NE FINISHED

How this triple was built (2 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: Mao Anhong | Statement: [Mao Zedong family, hasChildOfPatriarch, Mao Anhong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mao Anhong
Context triple: [Mao Zedong family, hasChildOfPatriarch, Mao Anhong]
  • A. Mao Anhong chosen
    Mao Anhong is a lesser-known son of Chinese Communist leader Mao Zedong and a member of the Mao family.
  • B. Mao Anqing
    Mao Anqing was the second son of Chinese Communist leader Mao Zedong, known for his work as a Russian-language translator and his relatively low political profile compared to his father.
  • C. Mao Xinyu
    Mao Xinyu is a Chinese major general and military historian best known as the grandson of Mao Zedong.
  • D. Yang Yuehua
    Yang Yuehua is a Chinese individual known primarily for being the sibling of former professional tennis star Li Na.
  • E. Wu Hong
    Wu Hong is a Chinese art historian and curator renowned for his scholarship on traditional and contemporary Chinese art.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69b3451886588190a3dd1305ea7c58dc completed March 12, 2026, 10:58 p.m.
NER Named-entity recognition batch_69b3563eab24819088add9180af2ce3c completed March 13, 2026, 12:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69b650abb8ec8190afb55dc0091f8415 completed March 15, 2026, 6:24 a.m.
Created at: March 12, 2026, 11:11 p.m.