Triple
T9804164
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Libyan airport network |
E237911
|
entity |
| Predicate | hasComponent |
P35
|
FINISHED |
| Object |
Brak Airport
Brak Airport is a regional airport in Libya that serves the town of Brak and its surrounding area.
|
E824654
|
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: Brak Airport | Statement: [Libyan airport network, hasComponent, Brak Airport]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brak Airport Context triple: [Libyan airport network, hasComponent, Brak Airport]
-
A.
Nowra Airport
Nowra Airport is a regional airfield in New South Wales, Australia, serving the town of Nowra and surrounding areas for civil and military aviation operations.
-
B.
Muanda Airport
Muanda Airport is a public airport serving the coastal town of Muanda in the western Democratic Republic of the Congo, providing regional air connectivity for passengers and cargo.
-
C.
Ulei Airport
Ulei Airport is a small regional airfield serving the island of Ambrym in Vanuatu, providing local and inter-island air connections.
-
D.
Baljek Airport
Baljek Airport is a small regional airport serving the town of Tura and the surrounding Garo Hills region in the Indian state of Meghalaya.
-
E.
Iki Airport
Iki Airport is a regional airport in Nagasaki Prefecture, Japan, providing air transport services to and from Iki Island.
- 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: Brak Airport Triple: [Libyan airport network, hasComponent, Brak Airport]
Generated description
Brak Airport is a regional airport in Libya that serves the town of Brak and its surrounding area.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Brak Airport Target entity description: Brak Airport is a regional airport in Libya that serves the town of Brak and its surrounding area.
-
A.
Nowra Airport
Nowra Airport is a regional airfield in New South Wales, Australia, serving the town of Nowra and surrounding areas for civil and military aviation operations.
-
B.
Muanda Airport
Muanda Airport is a public airport serving the coastal town of Muanda in the western Democratic Republic of the Congo, providing regional air connectivity for passengers and cargo.
-
C.
Ulei Airport
Ulei Airport is a small regional airfield serving the island of Ambrym in Vanuatu, providing local and inter-island air connections.
-
D.
Baljek Airport
Baljek Airport is a small regional airport serving the town of Tura and the surrounding Garo Hills region in the Indian state of Meghalaya.
-
E.
Iki Airport
Iki Airport is a regional airport in Nagasaki Prefecture, Japan, providing air transport services to and from Iki Island.
- 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_69ca84dd4608819097ff4ed00feca280 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdab7a0ce881908f0555d194dece3f |
completed | April 1, 2026, 11:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1d5aecdec81909fae349945406c6c |
completed | April 5, 2026, 3:23 a.m. |
| NEDg | Description generation | batch_69d1d6463fe481908e5d3f3fd22cffa4 |
completed | April 5, 2026, 3:25 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d1d6dc0bd8819082a5ad417ca87a76 |
completed | April 5, 2026, 3:28 a.m. |
Created at: March 30, 2026, 8:29 p.m.