Triple

T23162276
Position Surface form Disambiguated ID Type / Status
Subject Shō Shin E578617 entity
Predicate capital P234 FINISHED
Object Shuri 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: Shuri | Statement: [Shō Shin, capital, Shuri]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shuri
Context triple: [Shō Shin, capital, Shuri]
  • A. Shuri chosen
    Shuri is a historic town on Okinawa Island best known as the former royal capital of the Ryukyu Kingdom and the site of Shuri Castle.
  • B. Shuri
    Shuri is a brilliant Wakandan princess and tech genius in the Marvel Cinematic Universe, known especially for her cutting-edge inventions and support of Black Panther.
  • C. Keeya
    Keeya is the wife of Leota Adebayo, a character in the DC television series "Peacemaker."
  • D. Kiya
    Kiya was a lesser-known wife of the Egyptian pharaoh Akhenaten, often associated with the Amarna period and subject to scholarly debate regarding her origins and role at court.
  • E. Omi
    Omi is the central protagonist of the 2015 Indian romantic drama film "Love," around whom the story’s emotional and narrative arc revolves.
  • 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_69e245fc75348190a0288401044c8af8 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18f019cd881908e3c68d99454da2a completed April 29, 2026, 4:54 a.m.
Created at: April 17, 2026, 4:02 p.m.