Triple

T15549665
Position Surface form Disambiguated ID Type / Status
Subject Wu Ashun E370708 entity
Predicate name P16 FINISHED
Object Wu Ashun E370708 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: Wu Ashun | Statement: [Wu Ashun, name, Wu Ashun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wu Ashun
Context triple: [Wu Ashun, name, Wu Ashun]
  • A. Wu Ashun chosen
    Wu Ashun is a professional Chinese golfer known for his multiple victories on the European Tour.
  • B. Wu Jingyu
    Wu Jingyu is a Chinese taekwondo athlete and multiple-time Olympic gold medalist renowned as one of the sport’s most successful competitors.
  • C. Wu Yuxiang
    Wu Yuxiang was a 19th-century Chinese martial artist and scholar credited with founding the Wu (Hao) style of Tai Chi.
  • D. Liang Wengen
    Liang Wengen is a Chinese billionaire entrepreneur best known as the founder and chairman of Sany Group, one of the world’s leading heavy machinery manufacturers.
  • E. Wu Jianxiong
    Wu Jianxiong, better known as Chien-Shiung Wu, was a pioneering Chinese-American experimental physicist whose groundbreaking work on beta decay and the violation of parity conservation earned her the nickname "the First Lady of Physics."
  • 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_69d85cc6cf40819091f4a5facee1ebe6 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04a93121881909d88ca55a39252ac completed April 16, 2026, 2:33 a.m.
NED1 Entity disambiguation (via context triple) batch_6a003c4303888190a93830ef534715ae completed May 10, 2026, 8:05 a.m.
Created at: April 10, 2026, 4:08 a.m.