Triple
T7314671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rakiura National Park |
E168378
|
entity |
| Predicate | coversPercentageOfStewartIsland |
P41576
|
FINISHED |
| Object | about 85 percent |
—
|
LITERAL 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: about 85 percent | Statement: [Rakiura National Park, coversPercentageOfStewartIsland, about 85 percent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coversPercentageOfStewartIsland Context triple: [Rakiura National Park, coversPercentageOfStewartIsland, about 85 percent]
-
A.
coversPercentageOfIsland
chosen
Indicates the proportion of an island’s total area that is occupied or covered by a specified entity.
-
B.
relativeSizeComparedToNorthIsland
Indicates how the size of something compares to that of the North Island.
-
C.
percentageOfLandInNationalPark
Indicates the proportion of a given area’s total land that lies within designated national park boundaries.
-
D.
rankInSizeInNewZealandIslands
Indicates the ordinal position of an island in New Zealand when ordered by size (e.g., largest, second largest, etc.).
-
E.
distanceFromNewZealandMainland_km
Indicates the distance, measured in kilometers, between an entity’s location and the mainland of New Zealand.
- F. None of above.
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_69c68a5251508190ad68df4151cfeb04 |
completed | March 27, 2026, 1:46 p.m. |
| NER | Named-entity recognition | batch_69c6ec03a7248190beb1dec612725e5b |
completed | March 27, 2026, 8:43 p.m. |
| PD | Predicate disambiguation | batch_69c6e7705f4881909793071dee50c557 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 3:02 p.m.