Triple

T13482376
Position Surface form Disambiguated ID Type / Status
Subject Hikaru Genji E318402 entity
Predicate fictionalLover P110564 FINISHED
Object Fujitsubo NE NERFINISHED

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: Fujitsubo | Statement: [Hikaru Genji, fictionalLover, Fujitsubo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fujitsubo
Context triple: [Hikaru Genji, fictionalLover, Fujitsubo]
  • A. Furubira
    Furubira is a small coastal town in Hokkaido, Japan, known for its fishing industry and scenic seaside landscapes.
  • B. Takamikura
    Takamikura is the ornate imperial throne used in Kyoto for the enthronement ceremonies of Japanese emperors.
  • C. Fukutsu
    Fukutsu is a coastal city in southwestern Japan known for its beaches and location along the Genkai Sea in Fukuoka Prefecture.
  • D. Fukusaki
    Fukusaki is a town in Hyōgo Prefecture, Japan, known for its rural setting and association with folklorist Kunio Yanagita.
  • E. Fusokyo
    Fusokyo is a component or subdivision within Sect Shinto, a branch of Shinto characterized by organized religious groups with distinct doctrines and practices.
  • 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: Fujitsubo
Target entity description: Fujitsubo is a noblewoman in "The Tale of Genji," renowned as Hikaru Genji’s stepmother and forbidden love, whose resemblance to his mother drives much of the novel’s central emotional and moral conflict.
  • A. Furubira
    Furubira is a small coastal town in Hokkaido, Japan, known for its fishing industry and scenic seaside landscapes.
  • B. Takamikura
    Takamikura is the ornate imperial throne used in Kyoto for the enthronement ceremonies of Japanese emperors.
  • C. Fukutsu
    Fukutsu is a coastal city in southwestern Japan known for its beaches and location along the Genkai Sea in Fukuoka Prefecture.
  • D. Fukusaki
    Fukusaki is a town in Hyōgo Prefecture, Japan, known for its rural setting and association with folklorist Kunio Yanagita.
  • E. Fusokyo
    Fusokyo is a component or subdivision within Sect Shinto, a branch of Shinto characterized by organized religious groups with distinct doctrines and practices.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: fictionalLover
Context triple: [Hikaru Genji, fictionalLover, Fujitsubo]
  • A. fictionalGenre
    Indicates that a work of fiction belongs to or is categorized under a particular narrative genre or style.
  • B. fictionalNarrator
    Indicates that one entity serves as the narrator or storytelling voice within a fictional work that features the other entity.
  • C. fictionalUse
    Indicates that one entity makes use of another within a fictional or imaginary context, rather than in real-world usage.
  • D. fictionalMedium
    Indicates that a work of fiction is presented or conveyed through a particular medium or format (such as a book, film, game, or comic).
  • E. fictionalizationOf
    Indicates that one entity is a fictional or dramatized representation, adaptation, or reimagining of another (typically real or earlier) entity or event.
  • F. None of above. chosen

Provenance (4 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_69d806b6bfec819089222715b2e86c8e completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaf3868ec8190a6a1803018d4f2d8 completed April 12, 2026, 2:42 p.m.
PD Predicate disambiguation batch_69dbae06061881909a6a6032e0507587 completed April 12, 2026, 2:36 p.m.
PDg Predicate description generation batch_69dbaecc98cc8190829f5be759c4f1e3 completed April 12, 2026, 2:40 p.m.
Created at: April 9, 2026, 9:42 p.m.