Triple
T21465839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North American least shrew |
E529591
|
entity |
| Predicate | family |
P566
|
FINISHED |
| Object | Soricidae |
—
|
NE NERFINISHED |
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: Soricidae | Statement: [North American least shrew, family, Soricidae]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Soricidae Context triple: [North American least shrew, family, Soricidae]
-
A.
Soricidae
chosen
Soricidae is the biological family comprising shrews, small insectivorous mammals known for their high metabolic rates and pointed snouts.
-
B.
Spalacidae
Spalacidae is a family of burrowing rodents, commonly known as mole-rats and blind mole-rats, adapted to a subterranean lifestyle.
-
C.
Muridae
Muridae is the largest family of rodents, encompassing mice, rats, and many related small mammals found worldwide.
-
D.
Mephitidae
Mephitidae is a family of mammals best known for skunks and their close relatives, characterized by their ability to spray a strong-smelling defensive secretion.
-
E.
Mustelidae
Mustelidae is a diverse family of small to medium-sized carnivorous mammals that includes weasels, otters, badgers, ferrets, and wolverines, known for their elongated bodies and often fierce hunting behavior.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c458133481908ae8b41a12c4edec |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9e9f1b3cc819092c200f09c6f461e |
completed | April 23, 2026, 9:44 a.m. |
Created at: April 16, 2026, 6:09 p.m.