Triple

T15654263
Position Surface form Disambiguated ID Type / Status
Subject Tianqi Emperor E376389 entity
Predicate mother P120 FINISHED
Object Lady Wang E376389 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: Lady Wang | Statement: [Tianqi Emperor, mother, Lady Wang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lady Wang
Context triple: [Tianqi Emperor, mother, Lady Wang]
  • A. Lady Wang chosen
    Lady Wang was a Ming dynasty noblewoman best known as the consort of the Taichang Emperor and the mother of the Tianqi Emperor.
  • B. Lady Wang
    Lady Wang was the mother of Emperor Xian, the last emperor of the Eastern Han dynasty in ancient China.
  • C. Lady Zhang
    Lady Zhang was the wife of Chinese warlord and military leader Wu Peifu, associated with the Beiyang government era in early 20th-century China.
  • D. Lady Chen
    Lady Chen was the mother of the Hongwu Emperor, founder of China’s Ming dynasty, and is remembered primarily for her role as the imperial matriarch of that ruling house.
  • E. Lady Dong
    Lady Dong was a consort of Emperor Ling of Han and the mother of one of his imperial offspring during the late Eastern Han dynasty in China.
  • 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_69d85cd1564c8190991adda63bfab4b0 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04ef089948190902ec22f4d7bc932 completed April 16, 2026, 2:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff6797954c8190ac05ee3db634efa7 completed May 9, 2026, 4:57 p.m.
Created at: April 10, 2026, 4:15 a.m.