Triple

T22050297
Position Surface form Disambiguated ID Type / Status
Subject Tangut script E544864 entity
Predicate usedInRegion P908 FINISHED
Object Shaanxi NE NERFINISHED

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: Shaanxi | Statement: [Tangut script, usedInRegion, Shaanxi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shaanxi
Context triple: [Tangut script, usedInRegion, Shaanxi]
  • A. Shaanxi Province chosen
    Shaanxi Province is a landlocked region in north-central China known for its historical capital Xi'an and the Terracotta Army of Emperor Qin Shi Huang.
  • B. Yang Province
    Yang Province was an ancient administrative region in southeastern China that encompassed parts of modern Jiangsu, Anhui, and surrounding areas during the Han and Three Kingdoms periods.
  • C. Kansu
    Kansu is a Turkish surname most notably associated with Şevket Aziz Kansu, a prominent Turkish academic and anthropologist.
  • D. Jiaozhi Province
    Jiaozhi Province was a Ming dynasty colonial administrative region established in northern Vietnam during the early 15th century.
  • E. Gansu Province
    Gansu Province is a north-central Chinese region historically significant as a Silk Road corridor and home to long stretches of the Great Wall and diverse desert and mountain landscapes.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e32445c8190ab97089b48a130bb completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128323fb08190b9592fd08a96cba0 completed April 28, 2026, 9:35 p.m.
Created at: April 16, 2026, 8:26 p.m.