Triple
T10789828
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Regno del Sud |
E254549
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Brindisi |
E131131
|
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: Brindisi | Statement: [Regno del Sud, capital, Brindisi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brindisi Context triple: [Regno del Sud, capital, Brindisi]
-
A.
Brindisi
chosen
Brindisi is a historic port city in southern Italy’s Apulia region, long serving as a key maritime gateway between Italy and the eastern Mediterranean.
-
B.
Nardò
Nardò is a historic town in Italy’s Apulia region, known for its Baroque architecture and location in the province of Lecce in the Salento area.
-
C.
Lecce
Lecce is a historic city in Italy’s Apulia region, renowned for its rich Baroque architecture and cultural heritage.
-
D.
Molfetta
Molfetta is a coastal city in the Apulia region of southern Italy, known for its historic old town, fishing port, and Adriatic seaside location.
-
E.
Taranto
Taranto is a historic coastal city in southern Italy known as a major naval and commercial hub and for its strategic position on the Gulf of Taranto.
- 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_69d6aa609f008190a294200aefcb7bd5 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d732f5b8248190a633dc44ae620a3a |
completed | April 9, 2026, 5:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3e6d27d8c8190b2c8ee9c54cf7fd1 |
completed | April 18, 2026, 8:17 p.m. |
Created at: April 8, 2026, 9:17 p.m.