Triple

T18971656
Position Surface form Disambiguated ID Type / Status
Subject 秩父宮雍仁親王 E464183 entity
Predicate education P5 FINISHED
Object 学習院 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: 学習院 | Statement: [秩父宮雍仁親王, education, 学習院]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 学習院
Context triple: [秩父宮雍仁親王, education, 学習院]
  • A. Kokugakuin University
    Kokugakuin University is a private Japanese university renowned for its programs in Shinto studies, Japanese history, and literature, located in Tokyo.
  • B. Gakushuin University
    Gakushuin University is a prestigious private university in Tokyo historically known for educating members of Japan’s imperial family and elite.
  • C. Gakushuin chosen
    Gakushuin is a prestigious Japanese educational institution in Tokyo historically known for educating members of the Imperial Family and the country’s elite.
  • D. Shoin University
    Shoin University is a Japanese private university located in Atsugi, Kanagawa Prefecture, known for its humanities and social sciences programs.
  • E. Showa University
    Showa University is a private Japanese university known for its strong focus on medical and health sciences education and research.
  • 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_69d8dd008af48190a97ff1c6488edf1b completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d61a8bbc8190881908a71e0f2a53 completed April 20, 2026, 7:30 a.m.
Created at: April 10, 2026, noon