Triple

T19529556
Position Surface form Disambiguated ID Type / Status
Subject Silla period E488622 entity
Predicate country P26 FINISHED
Object Silla 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: Silla | Statement: [Silla period, country, Silla]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Silla
Context triple: [Silla period, country, Silla]
  • A. Silla chosen
    Silla was an ancient Korean kingdom that unified most of the Korean Peninsula in the 7th century and played a central role in the development of early Korean culture, Buddhism, and statehood.
  • B. Sillas
    Sillas is a surname most notably associated with American actress Karen Sillas, known for her work in independent film and television.
  • C. Sitton
    Sitton is a surname of English origin borne by various notable individuals, including athletes and public figures.
  • D. Gofa
    Gofa is an Omotic language spoken primarily by the Gofa people in southwestern Ethiopia.
  • E. Cuna
    Cuna is an alternative name for the Guna, an Indigenous people of Panama and Colombia known for their autonomous island communities and vibrant textile art called molas.
  • 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_69d8e8da8bec819081f400199491ccc3 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6363dfd6c8190aaa0b374184965bb completed April 20, 2026, 2:20 p.m.
Created at: April 10, 2026, 1:41 p.m.