Triple

T13912158
Position Surface form Disambiguated ID Type / Status
Subject Miyoshi Umeki E334524 entity
Predicate familyName P18 FINISHED
Object Umeki
Umeki is a Japanese surname most notably associated with Academy Award–winning actress and singer Miyoshi Umeki.
 E1070764 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: Umeki | Statement: [Miyoshi Umeki, familyName, Umeki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Umeki
Context triple: [Miyoshi Umeki, familyName, Umeki]
  • A. Sachiko
    Sachiko is a Japanese feminine given name that can be written with various kanji combinations, often conveying meanings related to happiness or child.
  • B. Shigeko
    Shigeko is a Japanese feminine given name that has been borne by various notable women, including members of the imperial family.
  • C. Noriko
    Noriko is a common Japanese feminine given name, often written with kanji conveying meanings such as "law," "order," or "child."
  • D. Takako
    Takako is a Japanese feminine given name borne by various notable figures in politics, arts, and entertainment.
  • E. Masako
    Masako is the Empress of Japan, a former diplomat and Harvard-educated member of the Imperial House known for her international background and public role.
  • 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: Umeki
Triple: [Miyoshi Umeki, familyName, Umeki]
Generated description
Umeki is a Japanese surname most notably associated with Academy Award–winning actress and singer Miyoshi Umeki.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Umeki
Target entity description: Umeki is a Japanese surname most notably associated with Academy Award–winning actress and singer Miyoshi Umeki.
  • A. Sachiko
    Sachiko is a Japanese feminine given name that can be written with various kanji combinations, often conveying meanings related to happiness or child.
  • B. Shigeko
    Shigeko is a Japanese feminine given name that has been borne by various notable women, including members of the imperial family.
  • C. Noriko
    Noriko is a common Japanese feminine given name, often written with kanji conveying meanings such as "law," "order," or "child."
  • D. Takako
    Takako is a Japanese feminine given name borne by various notable figures in politics, arts, and entertainment.
  • E. Masako
    Masako is the Empress of Japan, a former diplomat and Harvard-educated member of the Imperial House known for her international background and public role.
  • 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_69d81c5eaa9c819083b1ff8689179565 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2723461881908376b5509ee0d530 completed April 14, 2026, 11:38 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7ce783d808190b0e0ec89591af51d completed May 3, 2026, 10:38 p.m.
NEDg Description generation batch_69f7cf95e5a08190b264e543877d2852 completed May 3, 2026, 10:43 p.m.
NED2 Entity disambiguation (via description) batch_69fb5504702081908a1492f1a8e24434 completed May 6, 2026, 2:49 p.m.
Created at: April 9, 2026, 10:16 p.m.