Triple

T13824656
Position Surface form Disambiguated ID Type / Status
Subject Yikatong E332219 entity
Predicate transliteration P2508 FINISHED
Object Yīkǎtōng
Yīkǎtōng is a Chinese stored-value transportation and payment card system commonly used for public transit and small purchases in various cities.
 E1063776 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: Yīkǎtōng | Statement: [Yikatong, transliteration, Yīkǎtōng]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Yīkǎtōng
Context triple: [Yikatong, transliteration, Yīkǎtōng]
  • A. Tonghua
    Tonghua is a prefecture-level city in southeastern Jilin Province, China, known for its mountainous terrain, pharmaceutical industry, and role as a regional transportation hub.
  • B. Qitaihe
    Qitaihe is a small coal-mining city in northeastern China known for its rich mineral resources and location within Heilongjiang Province.
  • C. Kaihui
    Kaihui is a Chinese given name most notably borne by Yang Kaihui, the revolutionary and early partner of Mao Zedong.
  • D. Xingyuan
    Xingyuan was the Chinese era name used during part of Emperor Dezong of Tang’s reign in the late eighth century.
  • E. Yuanxing
    Yuanxing was the era name used by Eastern Wu emperor Sun Hao during part of his tumultuous late Three Kingdoms–period reign in China.
  • 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: Yīkǎtōng
Triple: [Yikatong, transliteration, Yīkǎtōng]
Generated description
Yīkǎtōng is a Chinese stored-value transportation and payment card system commonly used for public transit and small purchases in various cities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Yīkǎtōng
Target entity description: Yīkǎtōng is a Chinese stored-value transportation and payment card system commonly used for public transit and small purchases in various cities.
  • A. Tonghua
    Tonghua is a prefecture-level city in southeastern Jilin Province, China, known for its mountainous terrain, pharmaceutical industry, and role as a regional transportation hub.
  • B. Qitaihe
    Qitaihe is a small coal-mining city in northeastern China known for its rich mineral resources and location within Heilongjiang Province.
  • C. Kaihui
    Kaihui is a Chinese given name most notably borne by Yang Kaihui, the revolutionary and early partner of Mao Zedong.
  • D. Xingyuan
    Xingyuan was the Chinese era name used during part of Emperor Dezong of Tang’s reign in the late eighth century.
  • E. Yuanxing
    Yuanxing was the era name used by Eastern Wu emperor Sun Hao during part of his tumultuous late Three Kingdoms–period reign in China.
  • 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_69d81c5ae7c88190b0dd41bdafeb5999 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de0285fb7c8190be4b90bdc0d6fa53 completed April 14, 2026, 9:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b8e85c6c81908bdf5d43b917d151 completed May 3, 2026, 9:06 p.m.
NEDg Description generation batch_69f7b9d81f488190875e9b3f885556ab completed May 3, 2026, 9:10 p.m.
NED2 Entity disambiguation (via description) batch_69f7ba9ba0988190800e685cff4c2186 completed May 3, 2026, 9:14 p.m.
Created at: April 9, 2026, 10:13 p.m.