Triple
T6438961
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Formentera |
E129969
|
entity |
| Predicate | connectedByFerryTo |
P1831
|
FINISHED |
| Object | Denia |
E425416
|
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: Denia | Statement: [Formentera, connectedByFerryTo, Denia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Denia Context triple: [Formentera, connectedByFerryTo, Denia]
-
A.
Denia
chosen
Denia is a coastal city on Spain’s Costa Blanca known for its historic castle, Mediterranean beaches, and vibrant port.
-
B.
Benidorm
Benidorm is a major Spanish Mediterranean resort city famous for its skyscraper-lined beaches, vibrant nightlife, and mass tourism.
-
C.
Pietrasanta
Pietrasanta is a historic Tuscan town in Italy renowned for its marble workshops, sculpture studios, and vibrant community of international artists.
-
D.
Pietrasanta
Pietrasanta is an Italian surname of likely toponymic origin, associated with individuals such as Angela Maria Pietrasanta.
-
E.
Pollença
Pollença is a historic town in northern Mallorca, Spain, known for its charming stone streets, traditional architecture, and proximity to scenic coastal and mountain landscapes.
- 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_69c0084caac48190a7bc2ad8ba44536f |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c06965a5d48190a5860da9e22dc6e0 |
completed | March 22, 2026, 10:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c669de36a08190837817b32074e405 |
completed | March 27, 2026, 11:28 a.m. |
Created at: March 22, 2026, 4:45 p.m.