Triple
T17212417
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Capitán de Corbeta Carlos A. Curbelo International Airport |
E417763
|
entity |
| Predicate | ICAOcode |
P419
|
FINISHED |
| Object |
SULS
SULS is the ICAO airport code for Capitán de Corbeta Carlos A. Curbelo International Airport, serving the Punta del Este region in Uruguay.
|
E1257102
|
NE FINISHED |
How this triple was built (4 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: SULS | Statement: [Capitán de Corbeta Carlos A. Curbelo International Airport, ICAOcode, SULS]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SULS Context triple: [Capitán de Corbeta Carlos A. Curbelo International Airport, ICAOcode, SULS]
-
A.
Sulop
Sulop is a municipality in the province of Davao del Sur in the Philippines, known for its predominantly agricultural economy and rural communities.
-
B.
SUSU
SUSU is the students' union representing and supporting students at the University of Southampton through services, activities, and advocacy.
-
C.
SLD
SLD (Styled Layer Descriptor) is an OGC standard XML schema used to define the styling and visualization rules for geospatial data layers in web mapping services.
-
D.
SLD
SLD was a particle physics experiment at the SLAC Linear Collider that made precision measurements of electroweak interactions, including properties of the Z boson.
-
E.
SLD
SLD is a Polish social-democratic political party known as the Democratic Left Alliance.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: SULS Triple: [Capitán de Corbeta Carlos A. Curbelo International Airport, ICAOcode, SULS]
Generated description
SULS is the ICAO airport code for Capitán de Corbeta Carlos A. Curbelo International Airport, serving the Punta del Este region in Uruguay.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: SULS Target entity description: SULS is the ICAO airport code for Capitán de Corbeta Carlos A. Curbelo International Airport, serving the Punta del Este region in Uruguay.
-
A.
Sulop
Sulop is a municipality in the province of Davao del Sur in the Philippines, known for its predominantly agricultural economy and rural communities.
-
B.
SUSU
SUSU is the students' union representing and supporting students at the University of Southampton through services, activities, and advocacy.
-
C.
SLD
SLD (Styled Layer Descriptor) is an OGC standard XML schema used to define the styling and visualization rules for geospatial data layers in web mapping services.
-
D.
SLD
SLD is a Polish social-democratic political party known as the Democratic Left Alliance.
-
E.
SLD
SLD is the National Rail station code for Salford Crescent railway station in Greater Manchester, England.
- F. None of above. chosen
Provenance (5 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_69d886d779488190b131369541c04e7d |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42dc68a2c81908564231853b40db9 |
completed | April 19, 2026, 1:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01674fadc48190aa4a627ec9f72341 |
completed | May 11, 2026, 5:21 a.m. |
| NEDg | Description generation | batch_6a016826c4748190afbb4f6c53324d21 |
completed | May 11, 2026, 5:24 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0168d42b608190ad253167411dfeab |
completed | May 11, 2026, 5:27 a.m. |
Created at: April 10, 2026, 5:38 a.m.