Triple
T16691774
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Perdas Carpìas |
E405610
|
entity |
| Predicate | mountainRange |
P648
|
FINISHED |
| Object | Gennargentu |
E89857
|
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: Gennargentu | Statement: [Perdas Carpìas, mountainRange, Gennargentu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gennargentu Context triple: [Perdas Carpìas, mountainRange, Gennargentu]
-
A.
Gennargentu
chosen
Gennargentu is a rugged mountain massif in central Sardinia known for containing the island’s highest peaks and forming part of a major national park.
-
B.
Bollène
Bollène is a commune in southeastern France’s Vaucluse department, known for its historic old town and location near the Rhône River.
-
C.
Le Pouliguen
Le Pouliguen is a small seaside resort town on the Atlantic coast of western France, known for its beaches, harbor, and traditional Breton charm.
-
D.
Bois-du-Luc
Bois-du-Luc is a historic 19th-century coal mining complex in Wallonia, Belgium, preserved as an industrial heritage site and part of a UNESCO-listed mining landscape.
-
E.
Bénodet
Bénodet is a seaside resort town in Brittany, France, known for its beaches, marina, and coastal access to nearby Atlantic islands.
- 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_69d8838c28748190b3f5967c743940ab |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e37ea99bac8190a6c559ed7b7d8ecd |
completed | April 18, 2026, 12:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0091984dcc8190b0b20d2e57bc3a11 |
completed | May 10, 2026, 2:09 p.m. |
Created at: April 10, 2026, 5:19 a.m.