Triple

T13872688
Position Surface form Disambiguated ID Type / Status
Subject Wu Den-yih E333493 entity
Predicate givenName P17 FINISHED
Object Den-yih
Den-yih is the given name of Wu Den-yih, a Taiwanese politician who served as Vice President of the Republic of China (Taiwan).
E1065494 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: Den-yih | Statement: [Wu Den-yih, givenName, Den-yih]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Den-yih
Context triple: [Wu Den-yih, givenName, Den-yih]
  • A. Yih
    Yih is the surname of Chia-Shun Yih, a notable Chinese-American engineer and fluid dynamicist.
  • B. Deniyaya
    Deniyaya is a small town in southern Sri Lanka known as a primary gateway to the Sinharaja Forest Reserve, a UNESCO-listed tropical rainforest.
  • C. Yei
    Yei is a town in southwestern South Sudan that serves as a regional hub near the borders with Uganda and the Democratic Republic of the Congo.
  • D. S'Yan
    S'Yan is a former king of Wakanda and uncle to T'Challa in Marvel Comics' Black Panther mythos.
  • E. Ñuu Dzahui
    Ñuu Dzahui is the endonym used by the Mixtec people to refer to themselves and their traditional homeland in the region of present-day Oaxaca, Mexico.
  • 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: Den-yih
Triple: [Wu Den-yih, givenName, Den-yih]
Generated description
Den-yih is the given name of Wu Den-yih, a Taiwanese politician who served as Vice President of the Republic of China (Taiwan).
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Den-yih
Target entity description: Den-yih is the given name of Wu Den-yih, a Taiwanese politician who served as Vice President of the Republic of China (Taiwan).
  • A. Yih
    Yih is the surname of Chia-Shun Yih, a notable Chinese-American engineer and fluid dynamicist.
  • B. Deniyaya
    Deniyaya is a small town in southern Sri Lanka known as a primary gateway to the Sinharaja Forest Reserve, a UNESCO-listed tropical rainforest.
  • C. Yei
    Yei is a town in southwestern South Sudan that serves as a regional hub near the borders with Uganda and the Democratic Republic of the Congo.
  • D. S'Yan
    S'Yan is a former king of Wakanda and uncle to T'Challa in Marvel Comics' Black Panther mythos.
  • E. Ñuu Dzahui
    Ñuu Dzahui is the endonym used by the Mixtec people to refer to themselves and their traditional homeland in the region of present-day Oaxaca, Mexico.
  • 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_69d81c5ced9c8190b0e9bcc6effe5959 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de05c638248190bbe5d19f7b88d0f9 completed April 14, 2026, 9:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c107c20c81909dff0ca4a59fcc55 completed May 3, 2026, 9:41 p.m.
NEDg Description generation batch_69f7c20da9448190b3167b091bd39b94 completed May 3, 2026, 9:45 p.m.
NED2 Entity disambiguation (via description) batch_69f7c2cc63148190b9ca2828abe54286 completed May 3, 2026, 9:49 p.m.
Created at: April 9, 2026, 10:14 p.m.