Triple

T15327120
Position Surface form Disambiguated ID Type / Status
Subject Duchy of Gascony E366439 entity
Predicate historicalRegionOverlap P13711 FINISHED
Object Biscay E159064 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: Biscay | Statement: [Duchy of Gascony, historicalRegionOverlap, Biscay]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Biscay
Context triple: [Duchy of Gascony, historicalRegionOverlap, Biscay]
  • A. Biscay chosen
    Biscay is a coastal province in northern Spain, known for its capital Bilbao and its role as a historic and cultural center of the Basque Country.
  • B. Leioa
    Leioa is a suburban municipality in the Basque Country in northern Spain, located near Bilbao in the province of Biscay.
  • C. Abia
    Abia is a state in southeastern Nigeria known for its commercial hub Aba and its role in regional trade and industry.
  • D. Zuberoa
    Zuberoa is the Basque-language name for Soule, a small historical and cultural province of the Basque Country located in the French Pyrenees.
  • E. Garrotxa
    Garrotxa is a comarca (county) in northeastern Catalonia, Spain, known for its volcanic landscape, beech forests, and the medieval town of Besalú.
  • 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_69d85a121520819093dcce999fdefe1a completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03dffd6f88190a0f031ee90c6a7d2 completed April 16, 2026, 1:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69fef8add7088190b124bd4727bb2f28 completed May 9, 2026, 9:04 a.m.
Created at: April 10, 2026, 3:16 a.m.