Triple

T2477249
Position Surface form Disambiguated ID Type / Status
Subject Prince Higashifushimi Yorihito E55117 entity
Predicate givenName P17 FINISHED
Object Yorihito
Yorihito was a Japanese imperial prince of the Higashifushimi-no-miya house who served as a high-ranking naval officer during the late Meiji and Taishō periods.
E329011 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: Yorihito | Statement: [Prince Higashifushimi Yorihito, givenName, Yorihito]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yorihito
Context triple: [Prince Higashifushimi Yorihito, givenName, Yorihito]
  • A. Kenjirō
    Kenjirō is a Japanese masculine given name that can be written with various kanji combinations and is borne by multiple notable individuals in fields such as sports, arts, and entertainment.
  • B. Shinpei
    Shinpei is a Japanese given name commonly used for males and borne by various notable figures in politics, arts, and entertainment.
  • C. Shintaro
    Shintaro is a Japanese given name commonly used for males and borne by various notable figures in sports, entertainment, and politics.
  • D. Yoshihisa
    Yoshihisa is a Japanese given name commonly used for males.
  • E. Kentarō
    Kentarō is a Japanese given name commonly used for males, often associated with traditional or strong-sounding name combinations.
  • 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: Yorihito
Triple: [Prince Higashifushimi Yorihito, givenName, Yorihito]
Generated description
Yorihito was a Japanese imperial prince of the Higashifushimi-no-miya house who served as a high-ranking naval officer during the late Meiji and Taishō periods.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Yorihito
Target entity description: Yorihito was a Japanese imperial prince of the Higashifushimi-no-miya house who served as a high-ranking naval officer during the late Meiji and Taishō periods.
  • A. Kenjirō
    Kenjirō is a Japanese masculine given name that can be written with various kanji combinations and is borne by multiple notable individuals in fields such as sports, arts, and entertainment.
  • B. Shinpei
    Shinpei is a Japanese given name commonly used for males and borne by various notable figures in politics, arts, and entertainment.
  • C. Shintaro
    Shintaro is a Japanese given name commonly used for males and borne by various notable figures in sports, entertainment, and politics.
  • D. Yoshihisa
    Yoshihisa is a Japanese given name commonly used for males.
  • E. Kentarō
    Kentarō is a Japanese given name commonly used for males, often associated with traditional or strong-sounding name combinations.
  • 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_69ab49e279e88190ab10d7248aea9d11 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd14dde208190ad4e1c9de5d43b0a completed March 7, 2026, 7:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69b20f1e61308190be9604bce0be83d2 completed March 12, 2026, 12:55 a.m.
NEDg Description generation batch_69b210ea15788190aa00dcfaabcca47a completed March 12, 2026, 1:03 a.m.
NED2 Entity disambiguation (via description) batch_69b2117703b08190acb25f3f96469a1e completed March 12, 2026, 1:05 a.m.
Created at: March 6, 2026, 9:45 p.m.