Triple

T20645995
Position Surface form Disambiguated ID Type / Status
Subject Sejo of Joseon E507356 entity
Predicate eraName P2938 FINISHED
Object Sejo 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: Sejo | Statement: [Sejo of Joseon, eraName, Sejo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sejo
Context triple: [Sejo of Joseon, eraName, Sejo]
  • A. Sejo chosen
    Sejo was the seventh king of the Joseon Dynasty in Korea, known for usurping the throne from his young nephew and centralizing royal authority.
  • B. Sesia
    The Sesia is a river in northwestern Italy that flows through the Piedmont region before joining the Po River.
  • C. Ikva River
    The Ikva River is a waterway in western Ukraine that flows through the historic town of Kremenets and forms part of the region’s local river network.
  • D. Sebec River
    The Sebec River is a tributary in central Maine that drains Sebec Lake and flows westward to join the Piscataquis River within the larger Penobscot River system.
  • E. Tunge
    Tunge is a small locality in western Sweden situated within Lilla Edet Municipality in Västra Götaland County.
  • 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_69e0b4be702c8190a3d2410a881d310a completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6af1dd79481909de985d03ab861c2 completed April 20, 2026, 10:56 p.m.
Created at: April 16, 2026, 11:43 a.m.