Triple

T18205215
Position Surface form Disambiguated ID Type / Status
Subject HuBERT E435884 entity
Predicate hasAuthor P4244 FINISHED
Object Wei-Ning Hsu
Wei-Ning Hsu is a researcher in speech and audio processing, known for co-developing the HuBERT self-supervised learning model for speech representation.
E1316463 NE FINISHED

How this triple was built (4 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: Wei-Ning Hsu | Statement: [HuBERT, hasAuthor, Wei-Ning Hsu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wei-Ning Hsu
Context triple: [HuBERT, hasAuthor, Wei-Ning Hsu]
  • A. Tung-Yen Lin
    Tung-Yen Lin was a pioneering Chinese-American structural engineer renowned for his groundbreaking work in prestressed concrete and major bridge designs worldwide.
  • B. Chi-lung Shih
    Chi-lung Shih is the Wade–Giles romanization of Keelung City, a major port city in northern Taiwan.
  • C. Fu-Sheng Chiu
    Fu-Sheng Chiu is a film producer best known for his work on acclaimed Chinese-language cinema, including the internationally recognized drama "To Live."
  • D. Ching-Yun Hu
    Ching-Yun Hu is a Taiwanese-American concert pianist acclaimed for her international competition successes and performances with major orchestras worldwide.
  • E. Liang-Chieh Chen
    Liang-Chieh Chen is a computer vision and deep learning researcher known for influential work on neural network architectures and efficient models such as MobileNetV2.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Wei-Ning Hsu
Triple: [HuBERT, hasAuthor, Wei-Ning Hsu]
Generated description
Wei-Ning Hsu is a researcher in speech and audio processing, known for co-developing the HuBERT self-supervised learning model for speech representation.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Wei-Ning Hsu
Target entity description: Wei-Ning Hsu is a researcher in speech and audio processing, known for co-developing the HuBERT self-supervised learning model for speech representation.
  • A. Tung-Yen Lin
    Tung-Yen Lin was a pioneering Chinese-American structural engineer renowned for his groundbreaking work in prestressed concrete and major bridge designs worldwide.
  • B. Chi-lung Shih
    Chi-lung Shih is the Wade–Giles romanization of Keelung City, a major port city in northern Taiwan.
  • C. Fu-Sheng Chiu
    Fu-Sheng Chiu is a film producer best known for his work on acclaimed Chinese-language cinema, including the internationally recognized drama "To Live."
  • D. Ching-Yun Hu
    Ching-Yun Hu is a Taiwanese-American concert pianist acclaimed for her international competition successes and performances with major orchestras worldwide.
  • E. Liang-Chieh Chen
    Liang-Chieh Chen is a computer vision and deep learning researcher known for influential work on neural network architectures and efficient models such as MobileNetV2.
  • F. None of above. chosen

Provenance (5 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_69d8b90dba6481908e119eb9aa4ca0cb completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e222831081908f7d5500424e3acb completed April 19, 2026, 2:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03bb46f9048190b5d95b32e1a92703 completed May 12, 2026, 11:44 p.m.
NEDg Description generation batch_6a03bbe8e5148190ac3f0c247455cac0 completed May 12, 2026, 11:46 p.m.
NED2 Entity disambiguation (via description) batch_6a03bc66f81c8190bd47405d92e6547e completed May 12, 2026, 11:48 p.m.
Created at: April 10, 2026, 10:32 a.m.