Triple
T35656062
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | So.G.Aer S.p.A. |
E1030286
|
entity |
| Predicate | operatesPassengerTerminalAt |
P86510
|
FINISHED |
| Object | Cagliari Elmas 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: Cagliari Elmas Airport | Statement: [So.G.Aer S.p.A., operatesPassengerTerminalAt, Cagliari Elmas Airport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesPassengerTerminalAt Context triple: [So.G.Aer S.p.A., operatesPassengerTerminalAt, Cagliari Elmas Airport]
-
A.
hasPassengerTerminal
Indicates that one entity possesses or is equipped with a passenger terminal used for boarding, alighting, or handling passengers.
-
B.
passengerTerminalType
Indicates the specific kind or category of passenger terminal associated with an entity.
-
C.
operatesTerminalsIn
chosen
Indicates that an entity manages or runs the operations of one or more terminals at a given location or facility.
-
D.
hasPassengerTerminalFunction
Indicates that something serves the role or performs the function of a passenger terminal, supporting the handling and movement of passengers.
-
E.
architectOfPassengerTerminal
Indicates that an entity served as the architect responsible for designing a specific passenger terminal.
- 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_69f76e0938088190a8f199631e97dec3 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a016cc5abcc8190b64094c777b40f6f |
completed | May 11, 2026, 5:44 a.m. |
| PD | Predicate disambiguation | batch_6a016b997ecc8190818207c57b9cbf17 |
completed | May 11, 2026, 5:39 a.m. |
Created at: May 3, 2026, 4:05 p.m.