Triple

T12242778
Position Surface form Disambiguated ID Type / Status
Subject Turandot E291775 entity
Predicate character P662 FINISHED
Object Liù E293852 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: Liù | Statement: [Turandot, character, Liù]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liù
Context triple: [Turandot, character, Liù]
  • A. Liù chosen
    Liù is a gentle, self-sacrificing slave girl in Puccini’s opera "Turandot," known for her unwavering love and tragic death.
  • B. Fulin
    Fulin, better known by his temple name the Shunzhi Emperor, was the first Qing dynasty emperor to rule over China proper from Beijing in the mid-17th century.
  • C. Shizhen
    Shizhen is the given name of Li Shizhen, the renowned Ming dynasty physician and naturalist best known for compiling the monumental Chinese medical text "Compendium of Materia Medica."
  • D. Liang
    Liang is a common Chinese surname borne by numerous historical figures, scholars, and public personalities across the Chinese-speaking world.
  • E. Yuanhong
    Yuanhong is a Chinese given name that appears in the full name of the historical figure Li Yuanhong.
  • 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_69d6ab67950c8190be08450a06228c4b completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91cb724448190be29fc1d2b946ab7 completed April 10, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69f60ab5a404819089f9ea868deda10c completed May 2, 2026, 2:31 p.m.
Created at: April 8, 2026, 9:51 p.m.