Triple

T15276513
Position Surface form Disambiguated ID Type / Status
Subject Wu Jianxiong E365154 entity
Predicate nativeName P15 FINISHED
Object 吳健雄 E88969 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: 吳健雄 | Statement: [Wu Jianxiong, nativeName, 吳健雄]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 吳健雄
Context triple: [Wu Jianxiong, nativeName, 吳健雄]
  • A. 李遠哲
    李遠哲是一位以化學反應動力學研究聞名、曾獲諾貝爾化學獎的台灣科學家。
  • B. Chien-Shiung Wu chosen
    Chien-Shiung Wu was a pioneering Chinese-American experimental physicist whose groundbreaking work on beta decay and the violation of parity conservation made her one of the most influential physicists of the 20th century.
  • C. Wu Chien-lien
    Wu Chien-lien is a Taiwanese actress best known internationally for her acclaimed roles in films by director Ang Lee and in classic 1990s Chinese-language cinema.
  • D. Tsien Hsue-shen
    Tsien Hsue-shen was a pioneering Chinese aerospace engineer and rocket scientist who played a foundational role in both early American rocketry and the development of China’s missile and space programs.
  • E. L. C. Pei
    L. C. Pei is a Chinese-American architect best known for designing the iconic Bank of China Tower in Hong Kong.
  • 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_69d85a103d9081908c1ea6c4c73ac8e3 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e00953bc848190b83919f39d5ee37b completed April 15, 2026, 9:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69feef7186d481909067f8088f3ea497 completed May 9, 2026, 8:25 a.m.
Created at: April 10, 2026, 3:14 a.m.