Triple

T18360492
Position Surface form Disambiguated ID Type / Status
Subject Emperor Go-Sanjō E439900 entity
Predicate regnalName P744 FINISHED
Object Go-Sanjō 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: Go-Sanjō | Statement: [Emperor Go-Sanjō, regnalName, Go-Sanjō]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Go-Sanjō
Context triple: [Emperor Go-Sanjō, regnalName, Go-Sanjō]
  • A. Shirakawa-tennō
    Shirakawa-tennō was the 72nd emperor of Japan, known for initiating the insei (cloistered rule) system by abdicating the throne yet continuing to wield significant political power from behind the scenes in the late 11th and early 12th centuries.
  • B. Kiyosu
    Kiyosu is a city in central Japan known historically for Kiyosu Castle and its role as a political center during the Sengoku period.
  • C. Daijō
    Daijō is a Japanese term historically associated with imperial titles and court ranks, particularly in reference to retired emperors.
  • D. Later Sanjō chosen
    Later Sanjō is the posthumous name meaning "Later Sanjō" given to the Japanese Emperor Go-Sanjō, reflecting his association with the earlier Emperor Sanjō.
  • E. Ikeda Shōen
    Ikeda Shōen was a Japanese painter known for her contributions to Nihonga (modern Japanese-style painting) in the late 19th and early 20th centuries.
  • 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_69d8b918221c8190a9f7b563d64ac677 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e516db045c8190b20c209225a53b9a completed April 19, 2026, 5:54 p.m.
Created at: April 10, 2026, 10:37 a.m.