Triple

T16245343
Position Surface form Disambiguated ID Type / Status
Subject Emperor Shizong of Jin E394357 entity
Predicate familyName P18 FINISHED
Object Wanyan E1193696 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: Wanyan | Statement: [Emperor Shizong of Jin, familyName, Wanyan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wanyan
Context triple: [Emperor Shizong of Jin, familyName, Wanyan]
  • A. Wanyan chosen
    Wanyan is the clan name of the Jurchen ruling family that founded and governed the Jin dynasty in northern China during the 12th and 13th centuries.
  • B. Wanyan Aguda
    Wanyan Aguda was the Jurchen chieftain who rose to power in northern China by overthrowing the Liao dynasty and establishing the Jin dynasty in the early 12th century.
  • C. Wanyan Yongji
    Wanyan Yongji was an emperor of the Jurchen-led Jin dynasty in northern China whose troubled reign was marked by internal strife and devastating Mongol invasions.
  • D. Wanyan Zonggan
    Wanyan Zonggan was a Jurchen prince of the Jin dynasty and the son of Emperor Xizong of Jin.
  • E. Wanyan Zonghan
    Wanyan Zonghan was a prominent Jurchen Jin dynasty general best known for leading the invasion that captured the Northern Song capital during the Jingkang incident.
  • 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_69d87f2171208190951025e526947816 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e24561d250819096f709ea8751fcb9 completed April 17, 2026, 2:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00354ca28081908f993619a332cbf6 completed May 10, 2026, 7:35 a.m.
Created at: April 10, 2026, 5:04 a.m.