Triple
T4630291
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Half Moon Island |
E101396
|
entity |
| Predicate | hasWildlife |
P965
|
FINISHED |
| Object | Weddell seal |
E70182
|
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: Weddell seal | Statement: [Half Moon Island, hasWildlife, Weddell seal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Weddell seal Context triple: [Half Moon Island, hasWildlife, Weddell seal]
-
A.
Weddell seal
chosen
The Weddell seal is a large, deep-diving Antarctic seal species known for living year-round on sea ice and for its remarkable ability to vocalize underwater.
-
B.
crabeater seal
The crabeater seal is a highly abundant Antarctic seal species that primarily feeds on krill and is specially adapted to life on pack ice.
-
C.
leopard seal
The leopard seal is a large, powerful Antarctic marine predator known for its spotted coat and for preying on penguins and other seals.
-
D.
Antarctic fur seal
The Antarctic fur seal is a marine mammal of the Southern Ocean known for its dense fur, large breeding colonies, and recovery from historic overhunting.
-
E.
Baikal seal
The Baikal seal is a small, uniquely freshwater species of earless seal endemic to Russia’s Lake Baikal and adapted to its cold, deep waters.
- 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_69bd43d2f1c081908cd4b7ec48ecc73d |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd5a316ef48190831970ec914cf5a2 |
completed | March 20, 2026, 2:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bdfab992148190a1b1dfa33b971d11 |
completed | March 21, 2026, 1:56 a.m. |
Created at: March 20, 2026, 1:13 p.m.