Triple
T27562206
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adriatic-Ionian transport corridor |
E695802
|
entity |
| Predicate | connectsPortsIn |
P112572
|
FINISHED |
| Object | Italy |
—
|
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: Italy | Statement: [Adriatic-Ionian transport corridor, connectsPortsIn, Italy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsPortsIn Context triple: [Adriatic-Ionian transport corridor, connectsPortsIn, Italy]
-
A.
portConnections
chosen
Indicates that there exists a connection or linkage between two ports or interfaces.
-
B.
connectsPartOf
Indicates a relationship where one entity serves to link or join a component to the larger whole of which that component is a part.
-
C.
connectsPortToHinterland
Indicates that a port serves as a transport or logistical link to its surrounding inland (hinterland) region.
-
D.
linkedToPort
Indicates that one entity is connected or associated with a specific port, such as a network, hardware, or interface port.
-
E.
connectsTo
Indicates a relationship where one entity is linked or joined to another, allowing interaction, communication, or transfer between them.
- F. None of above.
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_69ef5387e97c8190a9dab040d21cd048 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69fccdd496048190bca801a8a9eecb62 |
completed | May 7, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69fcccee6240819084680887731ff64b |
completed | May 7, 2026, 5:33 p.m. |
Created at: April 27, 2026, 1:39 p.m.