Triple
T8069402
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Queen Beatrix International Airport |
E188330
|
entity |
| Predicate | IATAcode |
P418
|
FINISHED |
| Object |
AUA
AUA is the three-letter IATA airport code for Queen Beatrix International Airport, the main international gateway to the island of Aruba in the Caribbean.
|
E709627
|
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: AUA | Statement: [Queen Beatrix International Airport, IATAcode, AUA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AUA Context triple: [Queen Beatrix International Airport, IATAcode, AUA]
-
A.
AUA
AUA is the ICAO airline designator used to identify Austrian Airlines in international aviation operations.
-
B.
AAS
AAS is a major professional organization dedicated to the advancement of astronomy and related sciences in the United States.
-
C.
AAS
AAS is a pan-African scientific organization that promotes excellence in science, technology, and innovation to drive sustainable development across the African continent.
-
D.
AAS
AAS is a leading Australian scientific organization that promotes excellence in science, provides independent advice on scientific issues, and supports science education and public engagement.
-
E.
AAS
AAS is the abbreviation for the Austrian Academy of Sciences, Austria’s leading non-university institution for science and research.
- 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: AUA Triple: [Queen Beatrix International Airport, IATAcode, AUA]
Generated description
AUA is the three-letter IATA airport code for Queen Beatrix International Airport, the main international gateway to the island of Aruba in the Caribbean.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: AUA Target entity description: AUA is the three-letter IATA airport code for Queen Beatrix International Airport, the main international gateway to the island of Aruba in the Caribbean.
-
A.
AUA
AUA is the ICAO airline designator used to identify Austrian Airlines in international aviation operations.
-
B.
AAS
AAS is a major professional organization dedicated to the advancement of astronomy and related sciences in the United States.
-
C.
AAS
AAS is a pan-African scientific organization that promotes excellence in science, technology, and innovation to drive sustainable development across the African continent.
-
D.
AAS
AAS is a leading Australian scientific organization that promotes excellence in science, provides independent advice on scientific issues, and supports science education and public engagement.
-
E.
AAS
AAS is the abbreviation for the Austrian Academy of Sciences, Austria’s leading non-university institution for science and research.
- 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_69ca82b42674819086840efea12478e5 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3ffbd59c8190a34398ddb4ee551e |
completed | March 31, 2026, 3:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc63e9225c8190bb196d9c325bb85e |
completed | April 1, 2026, 12:16 a.m. |
| NEDg | Description generation | batch_69cc664234c08190852b1449b5880ecc |
completed | April 1, 2026, 12:26 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69cc674517b88190aa8fb73b0b8cf2ea |
completed | April 1, 2026, 12:31 a.m. |
Created at: March 30, 2026, 5:27 p.m.