Triple

T9553987
Position Surface form Disambiguated ID Type / Status
Subject Battle of Boulou E230493 entity
Predicate primaryObjectiveSpain P26024 FINISHED
Object maintain and consolidate Spanish gains in French Roussillon 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: maintain and consolidate Spanish gains in French Roussillon | Statement: [Battle of Boulou, primaryObjectiveSpain, maintain and consolidate Spanish gains in French Roussillon]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: primaryObjectiveSpain
Context triple: [Battle of Boulou, primaryObjectiveSpain, maintain and consolidate Spanish gains in French Roussillon]
  • A. strategicObjectiveSpain chosen
    Indicates that an entity has a strategic objective specifically related to Spain.
  • B. nationalGoalsForCatalonia
    Indicates a relationship where certain goals or objectives are designated as the national aims specifically for Catalonia.
  • C. obligationsOfSpain
    Indicates that certain duties, responsibilities, or commitments are borne by Spain in a given context.
  • D. returnToSpain
    Indicates that an entity goes back to Spain, typically after having been away.
  • E. effectOnSpain
    Indicates a relationship where one entity produces an influence, change, or consequence specifically affecting Spain.
  • 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_69ca847d3be8819099c9dad2a7e786f1 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd99217de48190b528e14fd02ee987 completed April 1, 2026, 10:16 p.m.
PD Predicate disambiguation batch_69ccd594d0ac8190a81bc11a3a538167 completed April 1, 2026, 8:21 a.m.
Created at: March 30, 2026, 8:02 p.m.