Triple

T30785731
Position Surface form Disambiguated ID Type / Status
Subject メタボリズム・グループ E783949 entity
Predicate 代表的な関連作品 P81108 FINISHED
Object 中銀カプセルタワービル LITERAL FINISHED

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: 中銀カプセルタワービル | Statement: [メタボリズム・グループ, 代表的な関連作品, 中銀カプセルタワービル]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: 代表的な関連作品
Context triple: [メタボリズム・グループ, 代表的な関連作品, 中銀カプセルタワービル]
  • A. アニメ作品との関係
    Indicates a relationship or association that an entity has with an anime work (e.g., as its creator, character, setting, or related production).
  • B. hasRelationToOtherWork chosen
    Indicates that one work bears a specified relationship (such as adaptation, sequel, reference, or influence) to another distinct work.
  • C. starringInRelatedWork
    Indicates that an entity appears as a star or lead performer in a work that is related to another primary work or context.
  • D. relatedToAuthorWork
    Indicates that there is a connection or association between an author and a work they have created, contributed to, or are otherwise linked with.
  • E. hasSequelOrRelated
    Indicates that one work follows, continues, or is otherwise narratively or thematically related to another work.
  • F. None of above.

Provenance (3 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_69f224b213c8819083886073f90b647e completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69f68fe8168c8190b083be0e33988b9c completed May 2, 2026, 11:59 p.m.
PD Predicate disambiguation batch_69f686140aa08190a35f62572b2db9b6 completed May 2, 2026, 11:17 p.m.
Created at: April 29, 2026, 8:41 p.m.