Triple

T20680354
Position Surface form Disambiguated ID Type / Status
Subject Rochefort E508274 entity
Predicate hasSubdivision P747 FINISHED
Object Han-sur-Lesse NE NERFINISHED

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: Han-sur-Lesse | Statement: [Rochefort, hasSubdivision, Han-sur-Lesse]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Han-sur-Lesse
Context triple: [Rochefort, hasSubdivision, Han-sur-Lesse]
  • A. Han-sur-Lesse chosen
    Han-sur-Lesse is a village in Wallonia, Belgium, best known for its extensive limestone cave system and underground river attractions.
  • B. Riec-sur-Bélon
    Riec-sur-Bélon is a coastal commune in the Finistère department of Brittany in northwestern France, known for its oyster farming and scenic river estuaries.
  • C. Hesbaye
    Hesbaye is a historical region in present-day Belgium, known for its fertile agricultural land and early medieval significance within the Frankish realms.
  • D. Wannebecq
    Wannebecq is a village in the municipality of Lessines in the Hainaut province of Wallonia, Belgium.
  • E. Oesling
    Oesling is the sparsely populated, hilly and forested northern region of Luxembourg, forming part of the Ardennes.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4c1164881909a3bf1e3ddb2bc32 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6bea655488190bab168d564d888af completed April 21, 2026, 12:02 a.m.
Created at: April 16, 2026, 11:44 a.m.