Triple

T22997526
Position Surface form Disambiguated ID Type / Status
Subject Princess Toshi E572542 entity
Predicate relative P37 FINISHED
Object Princess Kako 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: Princess Kako | Statement: [Princess Toshi, relative, Princess Kako]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Princess Kako
Context triple: [Princess Toshi, relative, Princess Kako]
  • A. Princess Kako chosen
    Princess Kako is a member of the Japanese imperial family and the second daughter of Crown Prince Fumihito and Crown Princess Kiko.
  • B. Princess Sachiko
    Princess Sachiko was a short-lived Japanese imperial princess, the daughter of Emperor Shōwa (Hirohito) and Empress Kōjun.
  • C. Princess Sayako
    Princess Sayako is the only daughter of Emperor Emeritus Akihito and Empress Emerita Michiko of Japan, known for relinquishing her imperial status upon marrying a commoner.
  • D. Princess Takako
    Princess Takako is a Japanese imperial family member and daughter of Emperor Hirohito, known for her role in Japan’s modern royal lineage.
  • E. Princess Takamado
    Princess Takamado is a member of the Japanese Imperial Family known for her extensive work in cultural exchange, sports promotion, and international goodwill activities.
  • 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_69e245b6a3ac81908087599eefe3e365 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f182f452b48190951fc5dde56c1bb2 completed April 29, 2026, 4:03 a.m.
Created at: April 17, 2026, 3:50 p.m.