Triple

T19301234
Position Surface form Disambiguated ID Type / Status
Subject San Leonardo de Yagüe E482700 entity
Predicate hasProvinceCapital P3433 FINISHED
Object Soria 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: Soria | Statement: [San Leonardo de Yagüe, hasProvinceCapital, Soria]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Soria
Context triple: [San Leonardo de Yagüe, hasProvinceCapital, Soria]
  • A. Soria chosen
    Soria is a historic and sparsely populated province in north-central Spain, known for its medieval heritage, natural landscapes, and role within the autonomous community of Castile and León.
  • B. Palencia
    Palencia is a historic city in northwestern Spain known for its Romanesque architecture and role as the capital of the province of the same name.
  • C. Palencia
    Palencia is a municipality and town located in the Guatemala Department of Guatemala, known for its rural character and proximity to Guatemala City.
  • D. Ciudad Real
    Ciudad Real is a historic provincial capital in central Spain known for its location on the Castilian plateau and its connections to the La Mancha region.
  • E. Pozorrubio
    Pozorrubio is a landlocked agricultural municipality in the province of Pangasinan in the Philippines, known for its crop production and rural communities.
  • 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_69d8e8d04d5c8190baa816986f2b1d1e completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fc8a2a5c8190bfe95e40d3c93a42 completed April 20, 2026, 10:14 a.m.
Created at: April 10, 2026, 1:31 p.m.