Triple

T20680367
Position Surface form Disambiguated ID Type / Status
Subject Rochefort E508274 entity
Predicate region P40 FINISHED
Object Condroz 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: Condroz | Statement: [Rochefort, region, Condroz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Condroz
Context triple: [Rochefort, region, Condroz]
  • A. Condroz chosen
    Condroz is a natural region of rolling hills and agricultural landscapes in southern Belgium, spanning parts of several provinces including Liège.
  • B. Binche
    Binche is a historic town in the Walloon region of Belgium, renowned for its well-preserved medieval architecture and its UNESCO-recognized Carnival of Binche.
  • C. Houdeng-Goegnies
    Houdeng-Goegnies is a village in the municipality of La Louvière in the province of Hainaut, Belgium, known for its proximity to the historic Canal du Centre and its boat lifts.
  • D. Buizingen
    Buizingen is a village and suburb of Halle in Flemish Brabant, Belgium, known in part for the 2010 train collision that occurred near its railway station.
  • E. Bottendorf
    Bottendorf is a locality in the German state of Thuringia that historically existed within the German Empire.
  • 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.