Triple

T1625089
Position Surface form Disambiguated ID Type / Status
Subject State of Chu E35122 entity
Predicate capital P234 FINISHED
Object Danyang
Danyang was an early capital city of the ancient Chinese State of Chu, significant in the formative period of the Chu kingdom’s political and cultural development.
E184511 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: Danyang | Statement: [State of Chu, capital, Danyang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Danyang
Context triple: [State of Chu, capital, Danyang]
  • A. Qianjiang
    Qianjiang is a city in China known for its regional industry and cultural exchanges, including international town twinning partnerships.
  • B. Jinling
    Jinling is an ancient name for the Chinese city now known as Nanjing, historically renowned as a major political and cultural center.
  • C. Yangsan
    Yangsan is a city in South Gyeongsang Province, South Korea, known as a growing residential and educational hub near Busan.
  • D. Zhenjiang
    Zhenjiang is a historic port city in eastern China known for its strategic location on the Yangtze River and its rich cultural and culinary heritage.
  • E. Luyang
    Luyang is a historic name associated with the city of Hefei, the capital of Anhui Province in eastern 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: Danyang
Triple: [State of Chu, capital, Danyang]
Generated description
Danyang was an early capital city of the ancient Chinese State of Chu, significant in the formative period of the Chu kingdom’s political and cultural development.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Danyang
Target entity description: Danyang was an early capital city of the ancient Chinese State of Chu, significant in the formative period of the Chu kingdom’s political and cultural development.
  • A. Qianjiang
    Qianjiang is a city in China known for its regional industry and cultural exchanges, including international town twinning partnerships.
  • B. Jinling
    Jinling is an ancient name for the Chinese city now known as Nanjing, historically renowned as a major political and cultural center.
  • C. Yangsan
    Yangsan is a city in South Gyeongsang Province, South Korea, known as a growing residential and educational hub near Busan.
  • D. Zhenjiang
    Zhenjiang is a historic port city in eastern China known for its strategic location on the Yangtze River and its rich cultural and culinary heritage.
  • E. Luyang
    Luyang is a historic name associated with the city of Hefei, the capital of Anhui Province in eastern 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_69a886023194819080a3fccd6e325d0e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a909d19b008190b2224717b2909a78 completed March 5, 2026, 4:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad58d12e808190a1319b1c87bcd22e completed March 8, 2026, 11:09 a.m.
NEDg Description generation batch_69ad59fede48819084a163ff73fbc1da completed March 8, 2026, 11:14 a.m.
NED2 Entity disambiguation (via description) batch_69ad5a85071c8190bab5cefcd918bb8d completed March 8, 2026, 11:16 a.m.
Created at: March 4, 2026, 7:28 p.m.