Triple
T8923704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Auderghem |
E212487
|
entity |
| Predicate | hasGreenSpace |
P1495
|
FINISHED |
| Object | Sonian Forest |
E576412
|
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: Sonian Forest | Statement: [Auderghem, hasGreenSpace, Sonian Forest]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sonian Forest Context triple: [Auderghem, hasGreenSpace, Sonian Forest]
-
A.
Sonian Forest
chosen
Sonian Forest is a large ancient woodland on the southeastern edge of Brussels, Belgium, known for its beech and oak trees and extensive recreational trails.
-
B.
Hallerbos forest
Hallerbos forest is a renowned woodland in Belgium famous for its spectacular springtime carpet of blooming bluebells that draws visitors and photographers from around the world.
-
C.
Forêt de Haguenau
Forêt de Haguenau is a large lowland forest in northeastern France, known for its extensive woodlands, biodiversity, and historical significance near the town of Haguenau in Alsace.
-
D.
Forêt d'Arc-en-Barrois
Forêt d'Arc-en-Barrois is a large deciduous forest in northeastern France known for its rich biodiversity and traditional hunting grounds.
-
E.
Marly Forest
Marly Forest is a historic woodland area in the Yvelines department of north-central France, known for its natural landscapes and former royal hunting grounds.
- 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_69ca839481d48190b42b037e0d0f636c |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6652d63881908821c8735984322a |
completed | April 1, 2026, 12:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfba5480d48190bf126caaa882d39e |
completed | April 3, 2026, 1:02 p.m. |
Created at: March 30, 2026, 6:56 p.m.