Triple

T1860696
Position Surface form Disambiguated ID Type / Status
Subject Tang dynasty E34804 entity
Predicate capital P234 FINISHED
Object Chang'an E155222 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: Chang'an | Statement: [Tang dynasty, capital, Chang'an]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Chang'an
Context triple: [Tang dynasty, capital, Chang'an]
  • A. Chang'an chosen
    Chang'an was the ancient capital of several Chinese dynasties and a major political, cultural, and trade center along the Silk Road.
  • B. Đông Đô
    Đông Đô was a historical name for the city now known as Hanoi, which has long served as a major political and cultural center of Vietnam.
  • C. Luoyang
    Luoyang is one of China’s oldest and most historically significant cities, renowned as an ancient imperial capital and cultural center along the Yellow River.
  • D. Xinjing
    Xinjing was the capital city of the Japanese puppet state of Manchukuo in northeastern China during the 1930s and early 1940s.
  • E. Kaifeng
    Kaifeng is an ancient city in eastern Henan, China, historically significant as a former capital of several Chinese dynasties and a major cultural and economic center.
  • 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_69a88600b2f88190bc09303e68ab517e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abb09caee881908efe8aa38471298c completed March 7, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae6522bb448190ae50a476da53fcda completed March 9, 2026, 6:13 a.m.
Created at: March 4, 2026, 7:34 p.m.