Triple

T18458618
Position Surface form Disambiguated ID Type / Status
Subject Yesün Temür E450970 entity
Predicate deathPlace P21 FINISHED
Object Shangdu 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: Shangdu | Statement: [Yesün Temür, deathPlace, Shangdu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shangdu
Context triple: [Yesün Temür, deathPlace, Shangdu]
  • A. Shangdu chosen
    Shangdu was the summer capital of Kublai Khan’s Yuan dynasty in China, later immortalized in Western literature as the fabled city of Xanadu.
  • B. Baidi City
    Baidi City is an ancient fortress and historical town in Fengjie County, Chongqing, China, famed as a cultural landmark overlooking the Yangtze River and associated with classic Chinese poetry and the Three Gorges region.
  • C. Yuan Dadu
    Yuan Dadu was the capital city of the Yuan dynasty in China, located on the site of present-day Beijing and serving as a major political and cultural center of the Mongol-ruled empire.
  • D. Dongjing
    Dongjing is the historical name for Kaifeng when it served as the capital of the Northern Song dynasty in China.
  • E. Wafangdian
    Wafangdian is a county-level city in Liaoning Province, China, known for its bearing industry and as an important satellite city of Dalian.
  • 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_69d8d38345688190b565eac2e4cd7935 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e52a7c18d88190ac17f58111722223 completed April 19, 2026, 7:18 p.m.
Created at: April 10, 2026, 11:31 a.m.