Triple
T3242302
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Province of Frosinone |
E67988
|
entity |
| Predicate | hasSpaTown |
P19664
|
FINISHED |
| Object | Fiuggi |
E346294
|
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: Fiuggi | Statement: [Province of Frosinone, hasSpaTown, Fiuggi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fiuggi Context triple: [Province of Frosinone, hasSpaTown, Fiuggi]
-
A.
Fiuggi
chosen
Fiuggi is an Italian spa town in the Lazio region, renowned for its mineral water springs and therapeutic treatments.
-
B.
Gubbio
Gubbio is a historic medieval town in the Umbria region of central Italy, known for its well-preserved stone architecture and traditional festivals.
-
C.
San Savino
San Savino is a small locality within the municipality of Predappio in the Emilia-Romagna region of northern Italy.
-
D.
Pisae
Pisae is the ancient Roman name for the city of Pisa in Tuscany, Italy, historically significant as a coastal settlement and later a prominent maritime republic.
-
E.
Fusignano
Fusignano is a small town in the Emilia-Romagna region of northern Italy, historically noted as the birthplace of Baroque composer Arcangelo Corelli.
- 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_69ad858d27348190abb61c280b4c86a9 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaf17463481909447f6ab46016407 |
completed | March 8, 2026, 5:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b3341597448190805ff43effb9070c |
completed | March 12, 2026, 9:45 p.m. |
Created at: March 8, 2026, 3:08 p.m.