Triple
T5750794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bay Islands |
E126845
|
entity |
| Predicate | hasAirport |
P105
|
FINISHED |
| Object |
Utila Airport
Utila Airport is a small regional airport serving the island of Utila in Honduras’ Bay Islands, primarily used by domestic flights and tourists visiting the island’s popular dive sites.
|
E543801
|
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: Utila Airport | Statement: [Bay Islands, hasAirport, Utila Airport]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Utila Airport Context triple: [Bay Islands, hasAirport, Utila Airport]
-
A.
Porvenir Airport
Porvenir Airport is a small regional airport serving the town of Porvenir in the Chilean region of Tierra del Fuego.
-
B.
Panguilemo Airport
Panguilemo Airport is a regional public airport serving the city of Talca and the surrounding Maule Region in central Chile.
-
C.
Maya-Maya Airport
Maya-Maya Airport is the main international airport serving Brazzaville, the capital city of the Republic of the Congo.
-
D.
Sauce Viejo Airport
Sauce Viejo Airport is a regional airport serving the city of Santa Fe and its surrounding area in Argentina.
-
E.
Arrecife Airport
Arrecife Airport is the main international airport serving the island of Lanzarote in Spain’s Canary Islands.
- 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: Utila Airport Triple: [Bay Islands, hasAirport, Utila Airport]
Generated description
Utila Airport is a small regional airport serving the island of Utila in Honduras’ Bay Islands, primarily used by domestic flights and tourists visiting the island’s popular dive sites.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Utila Airport Target entity description: Utila Airport is a small regional airport serving the island of Utila in Honduras’ Bay Islands, primarily used by domestic flights and tourists visiting the island’s popular dive sites.
-
A.
Porvenir Airport
Porvenir Airport is a small regional airport serving the town of Porvenir in the Chilean region of Tierra del Fuego.
-
B.
Panguilemo Airport
Panguilemo Airport is a regional public airport serving the city of Talca and the surrounding Maule Region in central Chile.
-
C.
Maya-Maya Airport
Maya-Maya Airport is the main international airport serving Brazzaville, the capital city of the Republic of the Congo.
-
D.
Sauce Viejo Airport
Sauce Viejo Airport is a regional airport serving the city of Santa Fe and its surrounding area in Argentina.
-
E.
Arrecife Airport
Arrecife Airport is the main international airport serving the island of Lanzarote in Spain’s Canary Islands.
- 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_69c00832aedc81909899801b141fa3b4 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0288a0ea8819091ac6f965471ceee |
completed | March 22, 2026, 5:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c07e3a50b88190a943b2d91d3c5b8e |
completed | March 22, 2026, 11:41 p.m. |
| NEDg | Description generation | batch_69c0880ef8608190a602c7b9c7f753fb |
completed | March 23, 2026, 12:23 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c088cff95481908a8e04e763269062 |
completed | March 23, 2026, 12:26 a.m. |
Created at: March 22, 2026, 3:48 p.m.