Triple
T16390966
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Queenstown Airport |
E398048
|
entity |
| Predicate | cityServed |
P82
|
FINISHED |
| Object | Frankton |
E565155
|
NE FINISHED |
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: Frankton | Statement: [Queenstown Airport, cityServed, Frankton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frankton Context triple: [Queenstown Airport, cityServed, Frankton]
-
A.
Frankton
chosen
Frankton is a lakeside suburb of Queenstown in New Zealand’s South Island, situated on the shores of Lake Wakatipu and known for its residential areas and proximity to the region’s main airport.
-
B.
Fullerville
Fullerville is a historic mill village and former industrial community that is now a notable historic site within Villa Rica, Georgia.
-
C.
Leudeville
Leudeville is a small commune in the Essonne department of the Île-de-France region in northern France.
-
D.
Tailleville
Tailleville is a small commune in the Calvados department of the Normandy region in northwestern France.
-
E.
Ville-au-Bois
Ville-au-Bois is a small settlement located within the municipality of Stoumont in the province of Liège, Belgium.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d87f2880b48190ae1a9673a3bbef80 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e326425c8081908cacffcfa8c7386b |
completed | April 18, 2026, 6:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00357167b881909a5182537ef973ce |
completed | May 10, 2026, 7:36 a.m. |
Created at: April 10, 2026, 5:08 a.m.