Triple

T3020513
Position Surface form Disambiguated ID Type / Status
Subject The Tale of Genji E82442 entity
Predicate author P4 FINISHED
Object Murasaki Shikibu E82443 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: Murasaki Shikibu | Statement: [The Tale of Genji, author, Murasaki Shikibu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Murasaki Shikibu
Context triple: [The Tale of Genji, author, Murasaki Shikibu]
  • A. Murasaki Shikibu chosen
    Murasaki Shikibu was a Japanese noblewoman and writer best known as the author of *The Tale of Genji*, often considered the world’s first novel.
  • B. Sei Shōnagon
    Sei Shōnagon was a Japanese court lady and writer best known for her witty and observant miscellany "The Pillow Book," a classic of Heian-era literature.
  • C. Ō no Yasumaro
    Ō no Yasumaro was an early 8th-century Japanese noble and scholar best known for compiling the Kojiki, one of Japan’s oldest extant chronicles of myths, legends, and early history.
  • D. Yamabe no Akahito
    Yamabe no Akahito was an early Nara-period Japanese court poet renowned for his elegant nature and landscape waka, many of which are preserved in the Man'yōshū anthology.
  • E. Ihara Saikaku
    Ihara Saikaku was a pioneering Japanese author of the Edo period, best known for his witty, realistic portrayals of urban merchant life and the pleasure quarters.
  • 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_69ad8b1fb34081908c1b873e2b7273e1 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad9a940c048190bc46e2c8001db8c0 completed March 8, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69b12e73b5988190be0712f4ddea92f7 completed March 11, 2026, 8:57 a.m.
Created at: March 8, 2026, 3 p.m.