Triple

T9889037
Position Surface form Disambiguated ID Type / Status
Subject Gan Chinese E181409 entity
Predicate dialectGroup P1254 FINISHED
Object Changdu Gan
Changdu Gan is a regional variety of the Gan branch of Chinese, spoken primarily in and around the Changdu area.
E827485 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: Changdu Gan | Statement: [Gan Chinese, dialectGroup, Changdu Gan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Changdu Gan
Context triple: [Gan Chinese, dialectGroup, Changdu Gan]
  • A. Xiaochang
    Xiaochang is a county in Hubei Province, China, known historically as a rural mission and teaching post where figures like Eric Liddell worked.
  • B. Chuanfang
    Chuanfang is the given name of Sun Chuanfang, a prominent Chinese warlord and military leader during the Warlord Era of early 20th-century China.
  • C. Changyi
    Changyi is a county-level coastal city in northeastern Shandong Province, China, known for its manufacturing industries and location on the Bohai Sea.
  • D. Youchang
    Youchang is the courtesy name of Ma Su, a Shu Han military general who served under Zhuge Liang during China’s Three Kingdoms period.
  • E. Guangqi
    Guangqi is the given name of Xu Guangqi, a prominent Ming dynasty scholar-official, scientist, and collaborator with Jesuit missionaries in introducing Western science to 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: Changdu Gan
Triple: [Gan Chinese, dialectGroup, Changdu Gan]
Generated description
Changdu Gan is a regional variety of the Gan branch of Chinese, spoken primarily in and around the Changdu area.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Changdu Gan
Target entity description: Changdu Gan is a regional variety of the Gan branch of Chinese, spoken primarily in and around the Changdu area.
  • A. Xiaochang
    Xiaochang is a county in Hubei Province, China, known historically as a rural mission and teaching post where figures like Eric Liddell worked.
  • B. Chuanfang
    Chuanfang is the given name of Sun Chuanfang, a prominent Chinese warlord and military leader during the Warlord Era of early 20th-century China.
  • C. Changyi
    Changyi is a county-level coastal city in northeastern Shandong Province, China, known for its manufacturing industries and location on the Bohai Sea.
  • D. Youchang
    Youchang is the courtesy name of Ma Su, a Shu Han military general who served under Zhuge Liang during China’s Three Kingdoms period.
  • E. Guangqi
    Guangqi is the given name of Xu Guangqi, a prominent Ming dynasty scholar-official, scientist, and collaborator with Jesuit missionaries in introducing Western science to 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_69ca8283a6708190801af7a25a7ebb9f completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cdb47be2988190811a99dc56ae542a completed April 2, 2026, 12:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1eb0314108190b35906592a11727e completed April 5, 2026, 4:54 a.m.
NEDg Description generation batch_69d1ebec25508190ac4c0adb629f79b0 completed April 5, 2026, 4:58 a.m.
NED2 Entity disambiguation (via description) batch_69d1ec65d5e881909e4caa180b0f8867 completed April 5, 2026, 5 a.m.
Created at: March 30, 2026, 8:39 p.m.