Triple

T9259498
Position Surface form Disambiguated ID Type / Status
Subject House of Reginar E222535 entity
Predicate powerBase P404 FINISHED
Object Louvain E78057 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: Louvain | Statement: [House of Reginar, powerBase, Louvain]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Louvain
Context triple: [House of Reginar, powerBase, Louvain]
  • A. Liège
    Liège is a major city in eastern Belgium known for its industrial heritage, vibrant cultural scene, and position along the Meuse River.
  • B. Leuven chosen
    Leuven is a historic Belgian city known for hosting KU Leuven, one of Europe’s leading research universities, and for its vibrant academic and cultural life.
  • C. Tervuren
    Tervuren is a municipality in Flemish Brabant, Belgium, known for its historic park, royal connections, and the Royal Museum for Central Africa.
  • D. Vilvoorde
    Vilvoorde is a city in the Flemish Region of Belgium, located just north of Brussels and known as part of the capital’s broader metropolitan area.
  • E. Braine-l'Alleud
    Braine-l'Alleud is a municipality in Walloon Brabant, Belgium, known for encompassing much of the historic Waterloo battlefield.
  • 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_69ca841e4cd481908e738c74e958eaea completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd07160e408190be4bd7b757260a0e completed April 1, 2026, 11:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1d58be8a4819088c419888a879e3e completed April 5, 2026, 3:22 a.m.
Created at: March 30, 2026, 7:32 p.m.