Triple

T15642324
Position Surface form Disambiguated ID Type / Status
Subject Yilan County E376097 entity
Predicate hasHotSpringArea P1094 FINISHED
Object Su’ao
Su’ao is a coastal township in northeastern Taiwan known for its cold springs, fishing harbor, and role as a transport hub in Yilan County.
E1170897 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: Su’ao | Statement: [Yilan County, hasHotSpringArea, Su’ao]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Su’ao
Context triple: [Yilan County, hasHotSpringArea, Su’ao]
  • A. Weida
    Weida is a river in eastern Germany that serves as a significant tributary of the Weiße Elster.
  • B. Liwan Dusun
    Liwan Dusun is a sub-ethnic group of the Kadazan-Dusun people of Sabah, Malaysia, with its own distinct dialect and cultural traditions.
  • C. Guisui
    Guisui was the historical name for the city now known as Hohhot, a major urban center in northern China.
  • D. Shancheng
    Shancheng is a Chinese nickname meaning "Mountain City," commonly used to refer to the city of Chongqing, known for its steep terrain and hilly urban landscape.
  • E. Bocheng
    Bocheng is a Chinese given name most notably borne by the prominent Communist military leader and strategist Liu Bocheng.
  • 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: Su’ao
Triple: [Yilan County, hasHotSpringArea, Su’ao]
Generated description
Su’ao is a coastal township in northeastern Taiwan known for its cold springs, fishing harbor, and role as a transport hub in Yilan County.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Su’ao
Target entity description: Su’ao is a coastal township in northeastern Taiwan known for its cold springs, fishing harbor, and role as a transport hub in Yilan County.
  • A. Weida
    Weida is a river in eastern Germany that serves as a significant tributary of the Weiße Elster.
  • B. Liwan Dusun
    Liwan Dusun is a sub-ethnic group of the Kadazan-Dusun people of Sabah, Malaysia, with its own distinct dialect and cultural traditions.
  • C. Guisui
    Guisui was the historical name for the city now known as Hohhot, a major urban center in northern China.
  • D. Shancheng
    Shancheng is a Chinese nickname meaning "Mountain City," commonly used to refer to the city of Chongqing, known for its steep terrain and hilly urban landscape.
  • E. Bocheng
    Bocheng is a Chinese given name most notably borne by the prominent Communist military leader and strategist Liu Bocheng.
  • 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_69d85cd035a48190b73d5579ab73969a completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04ed23d688190bea996f90989d406 completed April 16, 2026, 2:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff6ed079e48190b86ad7b66755fc1c completed May 9, 2026, 5:28 p.m.
NEDg Description generation batch_69ff6fa2b0b881908fa7af973ee0bb6f completed May 9, 2026, 5:32 p.m.
NED2 Entity disambiguation (via description) batch_69ff707d1db4819097aa9402ce0abb97 completed May 9, 2026, 5:35 p.m.
Created at: April 10, 2026, 4:15 a.m.