Triple

T6766126
Position Surface form Disambiguated ID Type / Status
Subject Imperial court of Japan E154722 entity
Predicate keyOffice P57682 FINISHED
Object Kampaku E408079 NE FINISHED

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: Kampaku | Statement: [Imperial court of Japan, keyOffice, Kampaku]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kampaku
Context triple: [Imperial court of Japan, keyOffice, Kampaku]
  • A. Kampaku chosen
    Kampaku was a powerful regent position in Japan’s imperial court, typically held by senior aristocrats who governed on behalf of an adult emperor.
  • B. Seishirō
    Seishirō is a Japanese given name commonly used for male individuals.
  • C. Fumimaro
    Fumimaro was a Japanese nobleman and politician who served multiple terms as Prime Minister of Japan in the years leading up to and during the early stages of World War II.
  • D. Michinaga
    Michinaga is the given name of Fujiwara no Michinaga, a powerful Heian-period Japanese court noble who dominated imperial politics at the height of the Fujiwara clan’s influence.
  • E. Kouaku
    Kouaku is one of the small islands that make up the remote Gambier Islands archipelago in French Polynesia.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c688109c1c8190added9a221292af0 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d22ed30881909e1bfcfb8cf175a2 completed March 27, 2026, 6:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69c71a7da01c8190995885eeb4ba6253 completed March 28, 2026, 12:02 a.m.
Created at: March 27, 2026, 2:12 p.m.