Triple

T5216156
Position Surface form Disambiguated ID Type / Status
Subject Segovia Province E117757 entity
Predicate capital P234 FINISHED
Object Segovia E151896 NE 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: Segovia | Statement: [Segovia Province, capital, Segovia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Segovia
Context triple: [Segovia Province, capital, Segovia]
  • A. Segovia chosen
    Segovia is a historic Spanish city in the region of Castile and León, renowned for its Roman aqueduct, medieval architecture, and well-preserved old town.
  • B. Ávila
    Ávila is a historic walled city in central Spain, renowned for its remarkably well-preserved medieval fortifications and Romanesque and Gothic architecture.
  • C. Badajoz
    Badajoz is a historic city in western Spain near the Portuguese border, known for its medieval fortress and role as a strategic frontier stronghold.
  • D. Burgos
    Burgos is a historic city in northern Spain known for its medieval architecture and its prominent role during the Spanish Civil War.
  • E. Henares
    Henares is a river in central Spain that flows through the Province of Guadalajara and is a tributary of the Jarama River.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69bd4464ba3c8190bc16b2ebbe42ddb0 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7a93fcc08190a1d2d025b4365d5a completed March 20, 2026, 4:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf3a86d58481909752c09fb9fec74e completed March 22, 2026, 12:40 a.m.
Created at: March 20, 2026, 1:48 p.m.