Triple

T19498047
Position Surface form Disambiguated ID Type / Status
Subject 義大犀牛 E487825 entity
Predicate 主場城市 P130903 FINISHED
Object 高雄市
高雄市は台湾南部に位置する港湾都市で、工業・貿易の拠点として発展しつつ観光や文化面でも知られる直轄市である。
E1379250 NE FINISHED

How this triple was built (5 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: 高雄市 | Statement: [義大犀牛, 主場城市, 高雄市]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 高雄市
Context triple: [義大犀牛, 主場城市, 高雄市]
  • A. 嘉義市
    嘉義市 is a county-level city in southwestern Taiwan known for its cultural heritage, historic sites, and role as a gateway to the Alishan scenic area.
  • B. 臺北市
    臺北市是臺灣的首都與最大都會區之一,為國家的政治、經濟、文化與交通中心。
  • C. 新竹市
    新竹市 is a city in northern Taiwan known for its high-tech industry hub, particularly the Hsinchu Science Park, and its strong education and research institutions.
  • D. 基隆
    基隆是位於臺灣北部的港口城市,以多雨氣候和重要海運樞紐地位聞名。
  • E. 臺北州
    臺北州 was an administrative division of Japanese-ruled Taiwan that encompassed the Taipei area during the colonial period.
  • 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: 高雄市
Triple: [義大犀牛, 主場城市, 高雄市]
Generated description
高雄市は台湾南部に位置する港湾都市で、工業・貿易の拠点として発展しつつ観光や文化面でも知られる直轄市である。
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 高雄市
Target entity description: 高雄市は台湾南部に位置する港湾都市で、工業・貿易の拠点として発展しつつ観光や文化面でも知られる直轄市である。
  • A. 嘉義市
    嘉義市 is a county-level city in southwestern Taiwan known for its cultural heritage, historic sites, and role as a gateway to the Alishan scenic area.
  • B. 臺北市
    臺北市是臺灣的首都與最大都會區之一,為國家的政治、經濟、文化與交通中心。
  • C. 新竹市
    新竹市 is a city in northern Taiwan known for its high-tech industry hub, particularly the Hsinchu Science Park, and its strong education and research institutions.
  • D. 基隆
    基隆是位於臺灣北部的港口城市,以多雨氣候和重要海運樞紐地位聞名。
  • E. 臺北州
    臺北州 was an administrative division of Japanese-ruled Taiwan that encompassed the Taipei area during the colonial period.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: 主場城市
Context triple: [義大犀牛, 主場城市, 高雄市]
  • A. cityOfHomeStadium chosen
    Indicates the city in which a given home stadium is located.
  • B. sponsorCity
    Indicates that an entity provides sponsorship or financial support to a particular city.
  • C. mainCityStadium
    Indicates that a stadium serves as the primary or main stadium for a given city.
  • D. occasionalHomeGroundCity
    Indicates that a location serves as a non-primary or infrequent home ground city for an entity, such as a sports team or organization.
  • E. hostTeamCity
    Indicates the city where the host team is based or where it plays its home events.
  • F. None of above.

Provenance (6 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_69d8e8d9d1c88190b01cd78b8be49384 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63493232881909fc33fb84da3e1b5 completed April 20, 2026, 2:13 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0740622cd88190965b3eb6e644cb6f completed May 15, 2026, 3:48 p.m.
NEDg Description generation batch_6a0744467d6c819082aa0933a0b9ba65 completed May 15, 2026, 4:05 p.m.
NED2 Entity disambiguation (via description) batch_6a0744ddbc3c8190b21d691a84e3ef92 completed May 15, 2026, 4:07 p.m.
PD Predicate disambiguation batch_69e4fd7bd25881908caa04eaef1f6718 completed April 19, 2026, 4:06 p.m.
Created at: April 10, 2026, 1:40 p.m.