Triple

T9083186
Position Surface form Disambiguated ID Type / Status
Subject Han Yu E217683 entity
Predicate chineseName P4878 FINISHED
Object 韓愈 E217683 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: 韓愈 | Statement: [Han Yu, chineseName, 韓愈]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 韓愈
Context triple: [Han Yu, chineseName, 韓愈]
  • A. Han Yu chosen
    Han Yu was a prominent Chinese writer, poet, and Confucian scholar of the Tang dynasty, renowned for championing classical prose and influencing later Neo-Confucian thought.
  • B. Ouyang Xiu
    Ouyang Xiu was an influential Song dynasty statesman, historian, and literary figure renowned for his prose, poetry, and role in shaping classical Chinese literature and scholarship.
  • C. Bai Juyi
    Bai Juyi was a prominent Chinese poet and official of the Tang dynasty, renowned for his accessible, socially conscious verse and enduring influence on East Asian literature.
  • D. Lu You
    Lu You was a prominent Southern Song dynasty poet renowned for his patriotic verse and prolific literary output.
  • E. Liu Ban
    Liu Ban was a Chinese scholar and official known for serving on the editorial team that compiled the historical chronicle Zizhi Tongjian.
  • 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_69ca83d7a0388190ba1af89ed7ba36f9 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc960a2760819084aab611eb1c43a9 completed April 1, 2026, 3:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69cffe30093481908b3ec394cf585642 completed April 3, 2026, 5:51 p.m.
Created at: March 30, 2026, 7:13 p.m.