Triple
T34359721
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Acipenser ruthenus |
E881838
|
entity |
| Predicate | barbels |
P88575
|
FINISHED |
| Object | four barbels in front of mouth |
—
|
LITERAL 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: four barbels in front of mouth | Statement: [Acipenser ruthenus, barbels, four barbels in front of mouth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: barbels Context triple: [Acipenser ruthenus, barbels, four barbels in front of mouth]
-
A.
hasBarbels
Indicates that an entity possesses barbels, i.e., whisker-like sensory appendages typically located near the mouth.
-
B.
rictalBristles
Indicates the presence of stiff, whisker-like feathers or bristles around the mouth or beak region of an organism.
-
C.
barbelCount
chosen
Indicates the number of barbels (whisker-like sensory organs) an entity possesses.
-
D.
hasBaleen
Indicates that one entity possesses baleen structures used for filter-feeding.
-
E.
hasAntennae
Indicates that one entity possesses or is equipped with antennae as a physical feature.
- F. None of above.
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_69f349be5c9c81908dc726ae1f4c68f2 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71c35327c8190884f1bfe12bd2cd7 |
completed | May 3, 2026, 9:58 a.m. |
| PD | Predicate disambiguation | batch_69f71822d0e88190ac9731c7ae5a4def |
completed | May 3, 2026, 9:40 a.m. |
Created at: May 1, 2026, 1:58 a.m.