Triple
T29487454
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Milan airport system |
E747968
|
entity |
| Predicate | hasDomesticConnectionsTo |
P1658
|
FINISHED |
| Object | major Italian cities |
—
|
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: major Italian cities | Statement: [Milan airport system, hasDomesticConnectionsTo, major Italian cities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDomesticConnectionsTo Context triple: [Milan airport system, hasDomesticConnectionsTo, major Italian cities]
-
A.
hasGeographicConnectionTo
Indicates a relationship where two entities are linked through a shared or relevant geographic feature, location, or spatial association.
-
B.
hasSeaRouteConnection
Indicates that there exists a navigable maritime route linking two locations or entities.
-
C.
hasDomesticFlights
chosen
Indicates that an airline or airport operates flights within the same country, connecting domestic destinations.
-
D.
hasLandsideConnection
Indicates that two locations are connected by a route or access on land, allowing movement between them without using air or water transport.
-
E.
hasAirTravelLink
Indicates that there is a direct or established air travel connection (such as flights or air routes) between the related entities.
- 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_69f0bd43ba30819095eb1cfc3adf525c |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca204148190850a3dc325bc07b7 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 28, 2026, 4:10 p.m.