Triple

T1603613
Position Surface form Disambiguated ID Type / Status
Subject Han dynasty E34448 entity
Predicate diplomaticRelation P15536 FINISHED
Object Dayuan E125348 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: Dayuan | Statement: [Han dynasty, diplomaticRelation, Dayuan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dayuan
Context triple: [Han dynasty, diplomaticRelation, Dayuan]
  • A. Jianye
    Jianye is an ancient name for the city now known as Nanjing, a historically significant capital in several Chinese dynasties.
  • B. Xinjing
    Xinjing was the capital city of the Japanese puppet state of Manchukuo in northeastern China during the 1930s and early 1940s.
  • C. Loulan chosen
    Loulan was an ancient Silk Road kingdom and oasis city in the eastern Tarim Basin, known for its strategic location and well-preserved archaeological remains.
  • D. Hexi District
    Hexi District is a central urban district of Tianjin, China, known for its commercial areas, educational institutions, and cultural sites along the Hai River.
  • E. Shangdu
    Shangdu was the summer capital of Kublai Khan’s Yuan dynasty in China, later immortalized in Western literature as the fabled city of Xanadu.
  • 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_69a885fea6a481909fe83ba6441f1774 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a9094f96ec819090286c21b3dfddd5 completed March 5, 2026, 4:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69ada0c3111081909bb8e503e77351cf completed March 8, 2026, 4:16 p.m.
Created at: March 4, 2026, 7:28 p.m.