Triple

T16206754
Position Surface form Disambiguated ID Type / Status
Subject Kanmu E393347 entity
Predicate spouse P13 FINISHED
Object Fujiwara no Otomuro E394946 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: Fujiwara no Otomuro | Statement: [Kanmu, spouse, Fujiwara no Otomuro]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fujiwara no Otomuro
Context triple: [Kanmu, spouse, Fujiwara no Otomuro]
  • A. Fujiwara no Otomuro chosen
    Fujiwara no Otomuro was a noblewoman of Japan’s powerful Fujiwara clan who became an empress consort during the early Heian period.
  • B. Fujiwara no Seishi
    Fujiwara no Seishi was a Heian-period Japanese noblewoman who became an empress consort and was a daughter of the powerful court regent Fujiwara no Michinaga.
  • C. Fujiwara no Kaneie
    Fujiwara no Kaneie was a powerful Heian-period Japanese court noble and regent whose political influence helped establish the dominance of the Fujiwara clan.
  • D. Fujiwara no Ishi
    Fujiwara no Ishi was a noblewoman of Japan's powerful Fujiwara clan who became a consort of Emperor Toba and an influential figure in the late Heian court.
  • E. Fujiwara no Tametoki
    Fujiwara no Tametoki was a Heian-period Japanese court noble and scholar best known as the father of the famed author Murasaki Shikibu.
  • 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_69d87f1f5bd08190bd01cac0d5b9d2ef completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e227101a3c819095ef40e50bf66433 completed April 17, 2026, 12:26 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0025f4f8708190ba1a08860e962c66 completed May 10, 2026, 6:30 a.m.
Created at: April 10, 2026, 5:03 a.m.