Triple

T987562
Position Surface form Disambiguated ID Type / Status
Subject Flanders E21312 entity
Predicate contains P35 FINISHED
Object Mechelen E101436 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: Mechelen | Statement: [Flanders, contains, Mechelen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mechelen
Context triple: [Flanders, contains, Mechelen]
  • A. Mechelen chosen
    Mechelen is a historic city in the Flemish region of Belgium, known for its rich architectural heritage, medieval center, and prominent role in the Low Countries’ political and religious history.
  • B. 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.
  • C. Leuven
    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.
  • D. Liège
    Liège is a major city in eastern Belgium known for its industrial heritage, vibrant cultural scene, and position along the Meuse River.
  • E. Hasselt
    Hasselt is a historic small city in the Dutch province of Overijssel, known for its medieval center and canals.
  • 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_69a493c383dc8190a03257f22d4b4183 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b4a7754c8190a10ba0587bd8323d completed March 1, 2026, 9:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad0e5948bc819085b3a68784e520c5 completed March 8, 2026, 5:51 a.m.
Created at: March 1, 2026, 7:41 p.m.