Triple
T37148121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Villesi |
E920294
|
entity |
| Predicate | associatedWithMainIslandConnection |
P133195
|
FINISHED |
| Object | Sicily |
E9715
|
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: Sicily | Statement: [Villesi, associatedWithMainIslandConnection, Sicily]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithMainIslandConnection Context triple: [Villesi, associatedWithMainIslandConnection, Sicily]
-
A.
associatedIsland
Indicates that one entity is related to or connected with a particular island in some relevant way.
-
B.
hasIslandConnection
chosen
Indicates that there exists a connection or link between entities that specifically involves or passes through an island.
-
C.
connectedToMainlandBy
Indicates that one landmass or area is physically linked to a mainland, typically via a bridge, causeway, or other continuous connection.
-
D.
hasNearbyMainIsland
Indicates that one entity has a main island located in close geographic proximity to it.
-
E.
isMainIsland
Indicates that an island is the primary or most significant island within a group, region, or country.
- F. None of above.
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_69f76e9f87c08190b4c8f7fafbd8345a |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a4035fcb5448190bb10235e034b5573 |
completed | June 27, 2026, 8:43 p.m. |
| PD | Predicate disambiguation | batch_6a037a11efc08190bb7cacc1325b4dc6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:15 p.m.