Triple
T1466601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stewart Island / Rakiura |
E27035
|
entity |
| Predicate | UlvaIslandInstanceOf |
P28868
|
FINISHED |
| Object | predator-free wildlife sanctuary |
—
|
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: predator-free wildlife sanctuary | Statement: [Stewart Island / Rakiura, UlvaIslandInstanceOf, predator-free wildlife sanctuary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: UlvaIslandInstanceOf Context triple: [Stewart Island / Rakiura, UlvaIslandInstanceOf, predator-free wildlife sanctuary]
-
A.
islandType
Indicates the specific classification or category of an island based on its characteristics or formation.
-
B.
hasIsland
Indicates that one entity possesses, contains, or includes an island as part of its domain, territory, or structure.
-
C.
partOfIsland
Indicates that one entity is a portion or component of an island.
-
D.
isIslandLike
Indicates that something has characteristics or qualities similar to those of an island, such as being isolated, surrounded, or distinct from its surroundings.
-
E.
isInIsland
Indicates that one entity is located within the geographic boundaries of an island.
- F. None of above. chosen
Provenance (4 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_69a496d25d6881909dbd84f86d763992 |
completed | March 1, 2026, 7:43 p.m. |
| NER | Named-entity recognition | batch_69a4c5bcfa0881909d6137c69825bc7a |
completed | March 1, 2026, 11:03 p.m. |
| PD | Predicate disambiguation | batch_69a4c48121e48190946c23c583e5fb64 |
completed | March 1, 2026, 10:58 p.m. |
| PDg | Predicate description generation | batch_69a4c55508948190922aee3230a4323e |
completed | March 1, 2026, 11:01 p.m. |
Created at: March 1, 2026, 8:01 p.m.