Triple

T3796281
Position Surface form Disambiguated ID Type / Status
Subject Empress Dowager Cixi E89777 entity
Predicate alsoKnownAs P39 FINISHED
Object Cixi Taihou E89777 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: Cixi Taihou | Statement: [Empress Dowager Cixi, alsoKnownAs, Cixi Taihou]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cixi Taihou
Context triple: [Empress Dowager Cixi, alsoKnownAs, Cixi Taihou]
  • A. Empress Dowager Cixi chosen
    Empress Dowager Cixi was a powerful and controversial late Qing dynasty ruler who effectively controlled the Chinese imperial government for nearly half a century.
  • B. Mao Ling
    Mao Ling is the mausoleum complex that serves as the imperial tomb of the Ming dynasty Chenghua Emperor in China.
  • C. Empress Ma
    Empress Ma was the consort of the Southern Ming Yongli Emperor and a prominent imperial figure during the dynasty’s final resistance against the Qing conquest.
  • D. Empress Ma
    Empress Ma was a prominent imperial consort of early Ming China, best known as the wife of the Hongwu Emperor and a key matriarchal figure in the dynasty’s founding generation.
  • E. Daizong
    Daizong is the posthumous temple name of the Ming dynasty's Jingtai Emperor, used in ancestral rites and historical records.
  • 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_69aed9597d6881909b6ee3b9de859223 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aee79f09bc8190b7514a11a030eba5 completed March 9, 2026, 3:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4f05ea5e081908c4714ca35aed48b completed March 14, 2026, 5:21 a.m.
Created at: March 9, 2026, 3:15 p.m.