Triple
T29487441
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Milan airport system |
E747968
|
entity |
| Predicate | lowCostGateway |
P60835
|
FINISHED |
| Object | Orio al Serio International Airport |
—
|
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: Orio al Serio International Airport | Statement: [Milan airport system, lowCostGateway, Orio al Serio International Airport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lowCostGateway Context triple: [Milan airport system, lowCostGateway, Orio al Serio International Airport]
-
A.
lowCostTerminal
Indicates that the terminal operates or is provided at a relatively low financial cost compared to alternatives.
-
B.
isLowCost
Indicates that something requires relatively little expenditure of money or resources compared to alternatives.
-
C.
hasLowCostCarrierFocus
Indicates that the subject is primarily oriented toward or strategically focused on serving low-cost carrier operations.
-
D.
fareLowerThan
Indicates that the fare associated with one entity is lower in cost than the fare associated with another entity.
-
E.
hasLowCostCarrierOperations
chosen
Indicates that an entity operates or is served by low-cost (budget) airline services.
- 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_69f66c06bbc48190b97efd782ebc81e6 |
completed | May 2, 2026, 9:26 p.m. |
| PD | Predicate disambiguation | batch_69f6633ac8a88190ab0cda62bbfcf9b0 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 4:10 p.m.