Triple

T5968007
Position Surface form Disambiguated ID Type / Status
Subject Prince Hitachi E132800 entity
Predicate familyName P18 FINISHED
Object Mikasa
Mikasa is a Japanese imperial family name most prominently associated with Prince Mikasa and his descendants within the modern Japanese monarchy.
 E559403 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: Mikasa | Statement: [Prince Hitachi, familyName, Mikasa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mikasa
Context triple: [Prince Hitachi, familyName, Mikasa]
  • A. Mikoto
    Mikoto is a divine title associated with the Shinto moon god Tsukuyomi, reflecting reverence and honor in Japanese mythology.
  • B. Mitsuru
    Mitsuru is a Japanese given name that can be used for people of any gender and is borne by various notable figures in sports, arts, and entertainment.
  • C. Tsutako
    Tsutako is a Japanese given name, most notably borne by Tsutako Nakasone.
  • D. Hatsuzuki
    Hatsuzuki was an Imperial Japanese Navy Akizuki-class destroyer that saw action in World War II before being sunk during the Battle off Cape Engaño in 1944.
  • E. Kaoru
    Kaoru is a central character in the later chapters of the classic Japanese novel "The Tale of Genji," known for his gentle nature and complex romantic entanglements.
  • 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: Mikasa
Triple: [Prince Hitachi, familyName, Mikasa]
Generated description
Mikasa is a Japanese imperial family name most prominently associated with Prince Mikasa and his descendants within the modern Japanese monarchy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mikasa
Target entity description: Mikasa is a Japanese imperial family name most prominently associated with Prince Mikasa and his descendants within the modern Japanese monarchy.
  • A. Mikoto
    Mikoto is a divine title associated with the Shinto moon god Tsukuyomi, reflecting reverence and honor in Japanese mythology.
  • B. Mitsuru
    Mitsuru is a Japanese given name that can be used for people of any gender and is borne by various notable figures in sports, arts, and entertainment.
  • C. Tsutako
    Tsutako is a Japanese given name, most notably borne by Tsutako Nakasone.
  • D. Hatsuzuki
    Hatsuzuki was an Imperial Japanese Navy Akizuki-class destroyer that saw action in World War II before being sunk during the Battle off Cape Engaño in 1944.
  • E. Kaoru
    Kaoru is a central character in the later chapters of the classic Japanese novel "The Tale of Genji," known for his gentle nature and complex romantic entanglements.
  • 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_69c0086deab081908550159ca23eec9b completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c03a3f612481908744cb645f2ede1d completed March 22, 2026, 6:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0e3ff62f08190be56bb9c450c9647 completed March 23, 2026, 6:55 a.m.
NEDg Description generation batch_69c0f61d80808190913b425c3c57f990 completed March 23, 2026, 8:13 a.m.
NED2 Entity disambiguation (via description) batch_69c0f6a75b908190b35d13b9593cf21f completed March 23, 2026, 8:15 a.m.
Created at: March 22, 2026, 4:03 p.m.