Triple

T21171656
Position Surface form Disambiguated ID Type / Status
Subject Wang Ji E521704 entity
Predicate name P16 FINISHED
Object Wang Ji 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: Wang Ji | Statement: [Wang Ji, name, Wang Ji]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wang Ji
Context triple: [Wang Ji, name, Wang Ji]
  • A. Wang Ji chosen
    Wang Ji was a Ming dynasty Confucian philosopher and prominent disciple of Wang Yangming who helped develop and transmit the School of Mind tradition.
  • B. Wang He
    Wang He was a military commander of the State of Qin during the Warring States period of ancient China, known for his role in the campaigns surrounding the Battle of Changping.
  • C. Wang Yo
    Wang Yo, better known by his temple name Gongyang of Goryeo, was the last king of Korea’s Goryeo dynasty before its fall to the Joseon dynasty.
  • D. Wu Ma
    Wu Ma was a prolific Hong Kong actor and film director, best known for his character roles in martial arts and supernatural comedies throughout the 1970s and 1980s.
  • E. Jiao Zhe
    Jiao Zhe is a Chinese former professional footballer best known for playing as a defender, primarily with Shandong Luneng Taishan in the Chinese Super League.
  • 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_69e0b50e30748190b186824a206d39b9 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7271351f08190b609a6c280c9a02a completed April 21, 2026, 7:28 a.m.
Created at: April 16, 2026, 3 p.m.