Triple
T15878024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donkey Kong Island |
E384998
|
entity |
| Predicate | invadedBy |
P3258
|
FINISHED |
| Object | Snowmads |
E1135598
|
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: Snowmads | Statement: [Donkey Kong Island, invadedBy, Snowmads]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Snowmads Context triple: [Donkey Kong Island, invadedBy, Snowmads]
-
A.
Snowmads
chosen
Snowmads are a Viking-themed animal invader faction that serves as the main enemy force in Donkey Kong Country: Tropical Freeze.
-
B.
Snowgoons
Snowgoons are a German hip hop production team known for their dark, orchestral boom-bap sound and collaborations with numerous underground rap artists worldwide.
-
C.
Snow Wonder
Snow Wonder is a 2005 made-for-television holiday drama film that intertwines multiple characters' lives during a Christmas Eve snowstorm.
-
D.
Snowdown
Snowdown is a former coal mining village in the Kent coalfield of southeast England, historically centered around Snowdown Colliery and its mining community.
-
E.
The Slopes
The Slopes is a historic landscaped park in Buxton, Derbyshire, known for its terraced walks, ornamental gardens, and views over the town’s spa architecture.
- 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_69d86da4e86481909f1325fdc971b5ec |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e155fec9d4819081efea504e1e3952 |
completed | April 16, 2026, 9:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffa950a890819092bc1e8895034593 |
completed | May 9, 2026, 9:38 p.m. |
Created at: April 10, 2026, 4:51 a.m.