Triple
T33264061
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AERIS Holdings Costa Rica |
E851598
|
entity |
| Predicate | airportOperated |
P38515
|
FINISHED |
| Object | Juan Santamaría 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: Juan Santamaría International Airport | Statement: [AERIS Holdings Costa Rica, airportOperated, Juan Santamaría International Airport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: airportOperated Context triple: [AERIS Holdings Costa Rica, airportOperated, Juan Santamaría International Airport]
-
A.
servesAsPrimaryAirportOperatorForCity
Indicates that an entity functions as the main organization responsible for operating the primary airport serving a particular city.
-
B.
operatesAirport
chosen
Indicates that one entity manages and runs the operations of an airport.
-
C.
airLegOperatedBy
Indicates that a specific segment (leg) of an air journey is operated by a particular airline or carrier.
-
D.
airBaseOperator
Indicates that one entity operates, manages, or is responsible for running an air base used for aviation activities.
-
E.
airlineOperationsType
Indicates the type or category of operational activities an airline conducts (e.g., passenger, cargo, charter, or mixed 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_69f349642dac81908a37ffcc3b976a55 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6ffbad8848190867c2988c0ceb84f |
completed | May 3, 2026, 7:56 a.m. |
| PD | Predicate disambiguation | batch_69f6fc5740fc81909774a4f65201a3ff |
completed | May 3, 2026, 7:42 a.m. |
Created at: May 1, 2026, 1:32 a.m.