Triple

T22267608
Position Surface form Disambiguated ID Type / Status
Subject Hosuseri E550389 entity
Predicate siblingOf P363 FINISHED
Object Hoori 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: Hoori | Statement: [Hosuseri, siblingOf, Hoori]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hoori
Context triple: [Hosuseri, siblingOf, Hoori]
  • A. Hoori chosen
    Hoori is a deity in Japanese mythology, known as a divine hunter and ancestor of Japan’s imperial line.
  • B. Hizaori
    Hizaori is the former name of Asaka, a city located in Saitama Prefecture, Japan.
  • C. Hodori
    Hodori is the friendly tiger character that served as the official mascot of the 1988 Seoul Olympic Games, symbolizing Korean hospitality and culture.
  • D. Hana-ogi
    Hana-ogi is a central Japanese geisha character in the novel and film "Sayonara," whose relationship with an American airman highlights themes of cross-cultural romance and postwar social tensions.
  • E. Yōrō
    Yōrō was a Japanese era of the Nara period, noted for administrative reforms and cultural development under imperial rule.
  • 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_69e11e43d8208190aff4f9cf7f2c2a8a completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f141bd0ea88190b3574883b695d56c completed April 28, 2026, 11:24 p.m.
Created at: April 16, 2026, 8:39 p.m.