Triple

T6563645
Position Surface form Disambiguated ID Type / Status
Subject 蔚山 E153846 entity
Predicate 下辖 P28620 FINISHED
Object 东区
东区是韩国蔚山广域市的一个行政区,以工业设施与港口经济为主。
E603028 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: 东区 | Statement: [蔚山, 下辖, 东区]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 东区
Context triple: [蔚山, 下辖, 东区]
  • A. 中央区
    中央区 is one of Tokyo’s 23 special wards, known as a major commercial and financial center that includes districts such as Ginza and Nihonbashi.
  • B. Zhongshan District
    Zhongshan District is a central urban district of Taipei, Taiwan, known for its mix of commercial areas, residential neighborhoods, and cultural attractions.
  • C. Central and Western District
    Central and Western District is a core urban area on Hong Kong Island that includes the city’s main financial, commercial, and historical centers such as Central and Sheung Wan.
  • D. 港区
    港区 is a central Tokyo ward known for its major business districts, embassies, upscale neighborhoods, and landmarks such as Roppongi and Tokyo Tower.
  • E. Yuexiu District
    Yuexiu District is a central urban district of Guangzhou, China, known for its political, commercial, and historical significance, including landmarks like Yuexiu Park and the Five Rams Statue.
  • 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: 东区
Triple: [蔚山, 下辖, 东区]
Generated description
东区是韩国蔚山广域市的一个行政区,以工业设施与港口经济为主。
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 东区
Target entity description: 东区是韩国蔚山广域市的一个行政区,以工业设施与港口经济为主。
  • A. 中央区
    中央区 is one of Tokyo’s 23 special wards, known as a major commercial and financial center that includes districts such as Ginza and Nihonbashi.
  • B. Zhongshan District
    Zhongshan District is a central urban district of Taipei, Taiwan, known for its mix of commercial areas, residential neighborhoods, and cultural attractions.
  • C. Central and Western District
    Central and Western District is a core urban area on Hong Kong Island that includes the city’s main financial, commercial, and historical centers such as Central and Sheung Wan.
  • D. 港区
    港区 is a central Tokyo ward known for its major business districts, embassies, upscale neighborhoods, and landmarks such as Roppongi and Tokyo Tower.
  • E. Yuexiu District
    Yuexiu District is a central urban district of Guangzhou, China, known for its political, commercial, and historical significance, including landmarks like Yuexiu Park and the Five Rams Statue.
  • 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_69c6880cb35881909b763eb0125236b9 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d0a262808190a33ac94374affde4 completed March 27, 2026, 6:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6d55fa1bc81908f2929e835051532 completed March 27, 2026, 7:07 p.m.
NEDg Description generation batch_69c6d676e43081909bf2a9cceff0b9b3 completed March 27, 2026, 7:11 p.m.
NED2 Entity disambiguation (via description) batch_69c6d843bad081909ebb887f32ea4195 completed March 27, 2026, 7:19 p.m.
Created at: March 27, 2026, 1:52 p.m.