Triple

T18467828
Position Surface form Disambiguated ID Type / Status
Subject Tugh Temür E451210 entity
Predicate reignName P32785 FINISHED
Object Tianli
Tianli was the era name used during part of the reign of Yuan dynasty emperor Tugh Temür in 14th-century China.
 E1326763 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: Tianli | Statement: [Tugh Temür, reignName, Tianli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tianli
Context triple: [Tugh Temür, reignName, Tianli]
  • A. Yingtian
    Yingtian was an important early Ming dynasty capital city, historically centered around present-day Nanjing in China.
  • B. Tianjuan
    Tianjuan was a historical Chinese era name used during the reign of Emperor Taizong of the Jurchen-led Jin dynasty.
  • C. Tianshi
    Tianshi was the reign era name used by Emperor Daowu, the founding ruler of the Northern Wei dynasty in early medieval China.
  • D. Wulian
    Wulian is a county-level city in eastern China’s Shandong province, known for its mountainous scenery and location on the Shandong Peninsula.
  • E. Tiant
    Tiant is a surname most notably associated with Cuban former Major League Baseball pitcher Luis Tiant, known for his distinctive delivery and success with the Boston Red Sox in the 1970s.
  • 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: Tianli
Triple: [Tugh Temür, reignName, Tianli]
Generated description
Tianli was the era name used during part of the reign of Yuan dynasty emperor Tugh Temür in 14th-century China.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tianli
Target entity description: Tianli was the era name used during part of the reign of Yuan dynasty emperor Tugh Temür in 14th-century China.
  • A. Yingtian
    Yingtian was an important early Ming dynasty capital city, historically centered around present-day Nanjing in China.
  • B. Tianjuan
    Tianjuan was a historical Chinese era name used during the reign of Emperor Taizong of the Jurchen-led Jin dynasty.
  • C. Tianshi
    Tianshi was the reign era name used by Emperor Daowu, the founding ruler of the Northern Wei dynasty in early medieval China.
  • D. Wulian
    Wulian is a county-level city in eastern China’s Shandong province, known for its mountainous scenery and location on the Shandong Peninsula.
  • E. Tiant
    Tiant is a surname most notably associated with Cuban former Major League Baseball pitcher Luis Tiant, known for his distinctive delivery and success with the Boston Red Sox in the 1970s.
  • 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_69d8d38465a0819099b9b42d2a662ac1 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e52a8459f88190a54cae4c8cb05119 completed April 19, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_6a043f24ff448190b1b54ff5209a7b01 completed May 13, 2026, 9:06 a.m.
NEDg Description generation batch_6a0465ffc3e48190b2e69cf482e49577 completed May 13, 2026, 11:52 a.m.
NED2 Entity disambiguation (via description) batch_6a04669583fc8190b32ce936b8bb0f63 completed May 13, 2026, 11:55 a.m.
Created at: April 10, 2026, 11:34 a.m.