Triple
T23365634
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Parktown |
E593310
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Killarney |
—
|
NE NERFINISHED |
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: Killarney | Statement: [Parktown, adjacentTo, Killarney]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Killarney Context triple: [Parktown, adjacentTo, Killarney]
-
A.
Killarney
Killarney is a popular tourist town in southwestern Ireland known for its lakes, national park, and scenic mountain landscapes.
-
B.
Killarney
Killarney is a primarily residential neighbourhood in southeast Vancouver, British Columbia, known for its parks, schools, and diverse community.
-
C.
Killarney
Killarney is a residential neighborhood in southwest Calgary, Alberta, known for its mix of older homes and newer infill developments close to the city core.
-
D.
Killarney
Killarney is a small Canadian community in Ontario known as a gateway to Georgian Bay and Killarney Provincial Park, popular for boating, hiking, and wilderness tourism.
-
E.
Killarney
chosen
Killarney is an affluent residential and commercial suburb of Johannesburg, South Africa, known for its apartment blocks and proximity to the city center.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e25d2593c88190bcdf4a716a94ccb2 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a0ab7fc481908b496ec9b543eddd |
completed | April 29, 2026, 6:09 a.m. |
Created at: April 17, 2026, 5:31 p.m.