Triple
T20533467
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isola di Gorgona |
E504127
|
entity |
| Predicate | belongsTo |
P35
|
FINISHED |
| Object | Comune di Livorno |
—
|
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: Comune di Livorno | Statement: [Isola di Gorgona, belongsTo, Comune di Livorno]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Comune di Livorno Context triple: [Isola di Gorgona, belongsTo, Comune di Livorno]
-
A.
Comune di Livorno
chosen
Comune di Livorno is the municipal government of the Italian port city of Livorno in Tuscany, responsible for local administration, services, and cultural heritage.
-
B.
Comune di Lucca
Comune di Lucca is the municipal government authority responsible for administering the historic Tuscan city of Lucca in central Italy.
-
C.
Comune di Viareggio
Comune di Viareggio is the municipal government authority of the coastal Tuscan city of Viareggio in Italy.
-
D.
Comune di Pisa
Comune di Pisa is the municipal government authority of the historic Italian city of Pisa in Tuscany.
-
E.
Comune di Firenze
Comune di Firenze is the municipal government of the city of Florence, responsible for its local administration, public services, and cultural heritage.
- 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_69e0b4b476648190bc6019622ae54d3c |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a06d30508190a13d1a9855b441fb |
completed | April 20, 2026, 9:53 p.m. |
Created at: April 16, 2026, 11:37 a.m.