Triple
T6139335
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southland |
E136918
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Fiordland |
E7893
|
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: Fiordland | Statement: [Southland, contains, Fiordland]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fiordland Context triple: [Southland, contains, Fiordland]
-
A.
Fiordland National Park
chosen
Fiordland National Park is a vast, rugged wilderness in New Zealand’s South Island, renowned for its dramatic fjords, towering mountains, ancient rainforests, and iconic sites like Milford Sound and Doubtful Sound.
-
B.
South Island
South Island is a volcanic island located within Kenya’s Lake Turkana, known for its stark lava landscapes and rich bird and crocodile populations.
-
C.
South Island
South Island is the larger of New Zealand’s two main islands, renowned for its dramatic mountains, fjords, and sparsely populated natural landscapes.
-
D.
South Island
South Island is one of the islands that make up Toronto’s waterfront Toronto Islands archipelago, known for its parkland and recreational spaces.
-
E.
Otago
Otago is a large region in the south of New Zealand known for its dramatic landscapes, historic gold-mining heritage, and the university city of Dunedin.
- 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_69c008a179388190a3b5a081bbf46d55 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c05c855a2481909801de9fd55686a4 |
completed | March 22, 2026, 9:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c518e697088190b47a610783baa7ea |
completed | March 26, 2026, 11:30 a.m. |
Created at: March 22, 2026, 4:15 p.m.