Triple
T18860274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Calasetta |
E461292
|
entity |
| Predicate | hasIslandConnection |
P133195
|
FINISHED |
| Object | connected by road bridge to Sant'Antioco |
—
|
LITERAL 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: connected by road bridge to Sant'Antioco | Statement: [Calasetta, hasIslandConnection, connected by road bridge to Sant'Antioco]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasIslandConnection Context triple: [Calasetta, hasIslandConnection, connected by road bridge to Sant'Antioco]
-
A.
hasIsland
Indicates that one entity possesses, contains, or includes an island as part of its domain, territory, or structure.
-
B.
hasIslandArc
Indicates that one geographic or geological entity possesses or is associated with an island arc feature.
-
C.
hasSisterIsland
Indicates that one island is considered a sister island of another, typically implying a special paired or closely associated relationship between them.
-
D.
hasIslandProvince
Indicates that a region or country possesses an administrative province that is located on an island.
-
E.
hasIslandOnOneSide
Indicates that one side of an object, area, or boundary is adjacent to or bordered by an island.
- F. None of above. chosen
Provenance (4 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_69d8dcfb7b9c8190854e7b171b98ea2e |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c05fb800819098951ec134a1fa2a |
completed | April 20, 2026, 5:57 a.m. |
| PD | Predicate disambiguation | batch_69e48d2166b88190add38de96cedc65c |
completed | April 19, 2026, 8:06 a.m. |
| PDg | Predicate description generation | batch_69e49785fd7081909577e90a55df0a35 |
completed | April 19, 2026, 8:51 a.m. |
Created at: April 10, 2026, 11:57 a.m.