Triple

T15286628
Position Surface form Disambiguated ID Type / Status
Subject Empress Sun E365417 entity
Predicate name P16 FINISHED
Object Empress Sun E365417 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: Empress Sun | Statement: [Empress Sun, name, Empress Sun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Empress Sun
Context triple: [Empress Sun, name, Empress Sun]
  • A. Empress Sun chosen
    Empress Sun was a Ming dynasty empress consort, best known as the principal wife of the Xuande Emperor and a prominent imperial figure in early 15th-century China.
  • B. Empress of Heaven
    Empress of Heaven is a divine title for Mazu, the revered Chinese sea goddess who protects sailors, fishermen, and coastal communities.
  • C. The Empress
    The Empress is a historic luxury hotel in Victoria, British Columbia, renowned for its grand Edwardian architecture and traditional afternoon tea service.
  • D. Princess of China
    "Princess of China" is a collaborative song by British rock band Coldplay and Barbadian singer Rihanna, featured on Coldplay's concept album *Mylo Xyloto*.
  • E. Empress Xiaochengjing
    Empress Xiaochengjing was a Ming dynasty empress consort known as the principal wife of the Hongzhi Emperor and mother of the Zhengde Emperor.
  • 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_69d85a103d9081908c1ea6c4c73ac8e3 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e00e551bb0819094db097285443740 completed April 15, 2026, 10:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69feef798a588190981c77e6f4c6be78 completed May 9, 2026, 8:25 a.m.
Created at: April 10, 2026, 3:15 a.m.