Triple

T3717564
Position Surface form Disambiguated ID Type / Status
Subject Gernika, Argentina E81566 entity
Predicate hasOriginOfName P3325 FINISHED
Object Basque immigration to Argentina LITERAL 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: Basque immigration to Argentina | Statement: [Gernika, Argentina, hasOriginOfName, Basque immigration to Argentina]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasOriginOfName
Context triple: [Gernika, Argentina, hasOriginOfName, Basque immigration to Argentina]
  • A. hasNameOrigin chosen
    Indicates that the origin or source of an entity’s name is specified by the related entity.
  • B. hasAcronymOrigin
    Indicates that an acronym is derived from or originates from a specific longer expression or name.
  • C. hasHistoricalOrigin
    Indicates that something originated, was first established, or came into existence during a specific historical period or context.
  • D. hasLanguageOfOrigin
    Indicates that one entity has its origin or source in the language specified by another entity.
  • E. hasBreedOrigin
    Indicates that an animal breed originates from or was first developed in a specified geographic location or cultural region.
  • F. None of above.

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_69ad8b1a81588190b3f27a5483bb610e completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adc9d087c881909f6d2ec6e518fb02 completed March 8, 2026, 7:11 p.m.
PD Predicate disambiguation batch_69adc0436e508190909ec4a3e8443aef completed March 8, 2026, 6:30 p.m.
Created at: March 8, 2026, 3:33 p.m.