Triple

T21439393
Position Surface form Disambiguated ID Type / Status
Subject 神戸大学 E528898 entity
Predicate hasFaculty P141 FINISHED
Object Faculty of Letters — NE NERFINISHED

How this triple was built (3 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: Faculty of Letters | Statement: [神戸大学, hasFaculty, Faculty of Letters]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Faculty of Letters
Context triple: [神戸大学, hasFaculty, Faculty of Letters]
  • A. Faculty of Letters
    The Faculty of Letters at Kobe University is an academic division specializing in humanities disciplines such as literature, history, philosophy, and related cultural studies.
  • B. Faculty of Letters
    The Faculty of Letters at Ankara University is a humanities-focused academic unit offering programs and research in fields such as language, literature, history, and cultural studies.
  • C. Faculty of Letters
    The Faculty of Letters at Doshisha University is a humanities-focused academic division offering programs in fields such as literature, philosophy, history, and related cultural studies.
  • D. Faculty of Letters
    The Faculty of Letters at Keio University is a humanities-focused academic division offering programs in fields such as literature, philosophy, history, and related cultural studies.
  • E. Faculty of Letters
    The Faculty of Letters is a humanities-focused academic division, typically offering programs in literature, languages, history, and related cultural studies.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Faculty of Letters
Target entity description: The Faculty of Letters at Kobe University is a humanities faculty offering education and research in fields such as literature, philosophy, history, and related cultural studies.
  • A. Faculty of Letters chosen
    The Faculty of Letters at Kobe University is an academic division specializing in humanities disciplines such as literature, history, philosophy, and related cultural studies.
  • B. Faculty of Letters
    The Faculty of Letters at Kyoto University is a humanities faculty renowned for its research and education in fields such as literature, philosophy, history, and cultural studies.
  • C. Faculty of Letters
    The Faculty of Letters at Kokugakuin University is an academic division focused on humanities disciplines such as literature, language, history, and related cultural studies.
  • D. Faculty of Letters
    The Faculty of Letters at Keio University is a humanities-focused academic division offering programs in fields such as literature, philosophy, history, and related cultural studies.
  • E. Faculty of Letters
    The Faculty of Letters at Gakushuin University is a humanities-focused academic division offering studies in fields such as literature, languages, history, and philosophy.
  • F. None of above.

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_69e0c4569fa081908101baa24f8745db completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e8b6feb2e48190ba5649f16a8bbbda completed April 22, 2026, 11:54 a.m.
Created at: April 16, 2026, 6:04 p.m.