Triple

T22926548
Position Surface form Disambiguated ID Type / Status
Subject Esen Taishi E569323 entity
Predicate title P38 FINISHED
Object Taishi
Taishi is a high-ranking title in East Asian historical contexts, often denoting a grand preceptor or supreme commander in imperial or nomadic political hierarchies.
E829493 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: Taishi | Statement: [Esen Taishi, title, Taishi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Taishi
Context triple: [Esen Taishi, title, Taishi]
  • A. Taishi
    Taishi is a town in Osaka Prefecture, Japan, known for its historical sites and traditional rural character.
  • B. Taishi
    Taishi was the first era name used by Emperor Wu of the Western Han dynasty, marking an important early phase of his long and influential reign in ancient China.
  • C. Huangtai
    Huangtai was the brief reign era name used by Emperor Gong, the last ruler of China’s Sui dynasty.
  • D. Taihoku
    Taihoku was the Japanese colonial-era name for Taipei, which served as the administrative and political center of Taiwan under Japanese rule.
  • E. Weishi
    Weishi is a Chinese Buddhist school that represents the East Asian transmission of Yogācāra (Consciousness-Only) philosophy, closely associated with the Hossō tradition in Japan.
  • 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: Taishi
Triple: [Esen Taishi, title, Taishi]
Generated description
Taishi is a high-ranking title in East Asian historical contexts, often denoting a grand preceptor or supreme commander in imperial or nomadic political hierarchies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Taishi
Target entity description: Taishi is a high-ranking title in East Asian historical contexts, often denoting a grand preceptor or supreme commander in imperial or nomadic political hierarchies.
  • A. Taishi
    Taishi is a town in Osaka Prefecture, Japan, known for its historical sites and traditional rural character.
  • B. Taishi chosen
    Taishi was the first era name used by Emperor Wu of the Western Han dynasty, marking an important early phase of his long and influential reign in ancient China.
  • C. Huangtai
    Huangtai was the brief reign era name used by Emperor Gong, the last ruler of China’s Sui dynasty.
  • D. Taihoku
    Taihoku was the Japanese colonial-era name for Taipei, which served as the administrative and political center of Taiwan under Japanese rule.
  • E. Weishi
    Weishi is a Chinese Buddhist school that represents the East Asian transmission of Yogācāra (Consciousness-Only) philosophy, closely associated with the Hossō tradition in Japan.
  • F. None of above.

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_69e2458f7d008190901dccbaebeaba24 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f180d90a9481908ea10019980b3951 completed April 29, 2026, 3:54 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bc2496f50819098e4bd9a3fa3f6e4 completed May 19, 2026, 1:52 a.m.
NEDg Description generation batch_6a0bc35c3ea08190a3b9111297774e6c completed May 19, 2026, 1:56 a.m.
NED2 Entity disambiguation (via description) batch_6a0bc43eafe081909dfff8b40d624635 completed May 19, 2026, 2 a.m.
Created at: April 17, 2026, 3:43 p.m.