Triple

T4231614
Position Surface form Disambiguated ID Type / Status
Subject Ala 31 E94592 entity
Predicate location P40 FINISHED
Object Zaragoza E55920 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: Zaragoza | Statement: [Ala 31, location, Zaragoza]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zaragoza
Context triple: [Ala 31, location, Zaragoza]
  • A. Zaragoza chosen
    Zaragoza is a historic city in northeastern Spain, known for landmarks like the Basilica del Pilar and its role as a major cultural and economic center in the Aragon region.
  • B. Burgos
    Burgos is a historic city in northern Spain known for its medieval architecture and its prominent role during the Spanish Civil War.
  • C. Vitoria-Gasteiz
    Vitoria-Gasteiz is a historic city in northern Spain that serves as the administrative capital of the Basque Autonomous Community and is known for its well-preserved medieval quarter and extensive green spaces.
  • D. Logroño
    Logroño is the capital city of Spain’s La Rioja region, renowned for its historic old town, vibrant tapas culture, and role as a key stop on the Camino de Santiago pilgrimage route.
  • E. Córdoba
    Córdoba is a major city in central Argentina known for its industrial base, universities, and strategic military presence.
  • 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_69b34537cc6481909cd0a96acbb33ef7 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b34e642aac8190977dd101e27afcbb completed March 12, 2026, 11:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5b77632d08190ab7c12986e2cee61 completed March 14, 2026, 7:31 p.m.
Created at: March 12, 2026, 11:05 p.m.