Triple

T22069385
Position Surface form Disambiguated ID Type / Status
Subject Xunzi E545363 entity
Predicate personalName P24312 FINISHED
Object Kuang 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: Kuang | Statement: [Xunzi, personalName, Kuang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kuang
Context triple: [Xunzi, personalName, Kuang]
  • A. Kuang chosen
    Kuang is the given name of Xunzi, a prominent Confucian philosopher of the Warring States period in ancient China.
  • B. Zhu Cihuan
    Zhu Cihuan was a Ming dynasty imperial prince, known primarily as a sibling of the famed Princess Changping during the dynasty’s final years.
  • C. Han Lue
    Han Lue is a laid-back, skilled street racer and heist crew member in the Fast & Furious franchise, known for his calm demeanor, drifting talent, and constant snacking.
  • D. He Zun
    He Zun is an ancient Western Zhou bronze ritual vessel renowned for bearing one of the earliest known inscriptions of the name “China” (Zhongguo).
  • E. Zhanran
    Zhanran was an influential 8th-century Chinese Buddhist monk and scholar who systematized and revitalized Tiantai doctrine, helping to secure the school’s later prominence.
  • 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_69e11e344dfc81909b1d88a7221329c7 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1288724e881908b38fe7e56d3b448 completed April 28, 2026, 9:37 p.m.
Created at: April 16, 2026, 8:28 p.m.