Triple
T14337399
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Somateria fischeri |
E355499
|
entity |
| Predicate | family |
P566
|
FINISHED |
| Object | Anatidae |
E94857
|
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: Anatidae | Statement: [Somateria fischeri, family, Anatidae]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anatidae Context triple: [Somateria fischeri, family, Anatidae]
-
A.
Anatidae
chosen
Anatidae is a large family of waterfowl that includes ducks, geese, and swans, many of which are adapted for aquatic habitats worldwide.
-
B.
Anseriformes
Anseriformes is an order of birds that includes ducks, geese, swans, and their relatives, many of which are adapted to aquatic environments.
-
C.
Glareolidae
Glareolidae is a family of birds known as pratincoles and coursers, characterized by their long wings, agile flight, and preference for open habitats such as grasslands and deserts.
-
D.
Gaviiformes
Gaviiformes is an order of aquatic birds known as loons or divers, characterized by their excellent diving ability and predominantly northern hemisphere distribution.
-
E.
Anserinae
Anserinae is a subfamily of waterfowl that includes swans and true geese within the duck, goose, and swan family Anatidae.
- 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_69d8278fa2108190bc0d0e7939c1eb03 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de8c2241e48190a0c626b3d741966a |
completed | April 14, 2026, 6:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd5bbb672c8190b25f7046500c56e2 |
completed | May 8, 2026, 3:42 a.m. |
Created at: April 10, 2026, 1:14 a.m.