Triple
T17412678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aubigny-sur-Nère |
E423407
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Sologne forest |
—
|
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: Sologne forest | Statement: [Aubigny-sur-Nère, locatedNear, Sologne forest]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sologne forest Context triple: [Aubigny-sur-Nère, locatedNear, Sologne forest]
-
A.
Sologne
chosen
Sologne is a rural region in central France known for its forests, lakes, and hunting estates.
-
B.
Forêt d’Écouves
Forêt d’Écouves is a large, historic forest in Normandy, France, known for its extensive woodlands, diverse wildlife, and role as a major natural area within the Orne department.
-
C.
Les Landes
Les Landes is a region in southwestern France known for its vast Atlantic coastline, extensive pine forests, and rural landscapes.
-
D.
Faux de Verzy forest
Faux de Verzy forest is a unique woodland in France renowned for its rare, twisted dwarf beech trees known as "faux de Verzy."
-
E.
Rambouillet Forest
Rambouillet Forest is a large historic woodland and former royal hunting ground in north-central France, known for its diverse wildlife and extensive network of trails.
- 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_69d889d7d27c819088486ce3f0627fa1 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43b0c12b881908b2ddc13678c7a75 |
completed | April 19, 2026, 2:16 a.m. |
Created at: April 10, 2026, 5:46 a.m.