Triple

T20303969
Position Surface form Disambiguated ID Type / Status
Subject Prince Takamado E505558 entity
Predicate familyName P18 FINISHED
Object Mikasa NE NERFINISHED

How this triple was built (2 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 Takamado, familyName, Mikasa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mikasa
Context triple: [Prince Takamado, familyName, Mikasa]
  • A. Mikasa chosen
    Mikasa is a Japanese imperial family name most prominently associated with Prince Mikasa and his descendants within the modern Japanese monarchy.
  • B. Mikasa
    Mikasa is a small city in Hokkaido, Japan, known for its coal mining history and rich fossil discoveries.
  • C. Mikoto
    Mikoto is a divine title associated with the Shinto moon god Tsukuyomi, reflecting reverence and honor in Japanese mythology.
  • D. 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.
  • E. Shirō
    Shirō is a Japanese given name most infamously associated with Shirō Ishii, the Imperial Japanese Army general who led the biological warfare research unit known as Unit 731 during World War II.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4b8ab648190906e18538c250148 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6773ed3248190ba949ec941e8d41f completed April 20, 2026, 6:58 p.m.
Created at: April 16, 2026, 11:17 a.m.