Triple

T17369643
Position Surface form Disambiguated ID Type / Status
Subject Emperor Antoku E422275 entity
Predicate associatedClan P1915 FINISHED
Object Taira
Taira was a powerful samurai clan that dominated late Heian-period Japanese politics and warfare before its downfall in the Genpei War.
E1266330 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: Taira | Statement: [Emperor Antoku, associatedClan, Taira]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Taira
Context triple: [Emperor Antoku, associatedClan, Taira]
  • A. Soga
    Soga is a Bantu language spoken primarily in eastern Uganda by the Basoga people.
  • B. Mutsu
    Mutsu was a Japanese Nagato-class battleship of the Imperial Japanese Navy that served prominently during the interwar period and World War II before being destroyed by an internal explosion in 1943.
  • C. Mutsu
    Mutsu is a coastal city in northern Japan known for its proximity to the Shimokita Peninsula and natural hot springs.
  • D. Arinori
    Arinori was a given name of Mori Arinori, a prominent Meiji-era Japanese statesman and reformer known for modernizing Japan’s education system.
  • E. Enryaku
    Enryaku was a Japanese era during the reign of Emperor Kanmu, notable for major political reforms and the early development of Kyoto as the imperial capital.
  • 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: Taira
Triple: [Emperor Antoku, associatedClan, Taira]
Generated description
Taira was a powerful samurai clan that dominated late Heian-period Japanese politics and warfare before its downfall in the Genpei War.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Taira
Target entity description: Taira was a powerful samurai clan that dominated late Heian-period Japanese politics and warfare before its downfall in the Genpei War.
  • A. Soga
    Soga is a Bantu language spoken primarily in eastern Uganda by the Basoga people.
  • B. Mutsu
    Mutsu was a Japanese Nagato-class battleship of the Imperial Japanese Navy that served prominently during the interwar period and World War II before being destroyed by an internal explosion in 1943.
  • C. Mutsu
    Mutsu is a coastal city in northern Japan known for its proximity to the Shimokita Peninsula and natural hot springs.
  • D. Arinori
    Arinori was a given name of Mori Arinori, a prominent Meiji-era Japanese statesman and reformer known for modernizing Japan’s education system.
  • E. Enryaku
    Enryaku was a Japanese era during the reign of Emperor Kanmu, notable for major political reforms and the early development of Kyoto as the imperial capital.
  • 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_69d889d6535c81908be333c01deaec4e completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a6842388190940235198fa50041 completed April 19, 2026, 2:14 a.m.
NED1 Entity disambiguation (via context triple) batch_6a019fed4ee88190bdbf3b31b3d5e3a0 completed May 11, 2026, 9:22 a.m.
NEDg Description generation batch_6a01a089ac0081908a746c0c25cc12be completed May 11, 2026, 9:25 a.m.
NED2 Entity disambiguation (via description) batch_6a01a1c415dc8190ba8f7e2a8053917f completed May 11, 2026, 9:30 a.m.
Created at: April 10, 2026, 5:44 a.m.