Triple
T14700233
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Desmoulin’s whorl snail |
E345275
|
entity |
| Predicate | shellSize |
P28652
|
FINISHED |
| Object | approximately 2 millimetres to 3 millimetres in height |
—
|
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: approximately 2 millimetres to 3 millimetres in height | Statement: [Desmoulin’s whorl snail, shellSize, approximately 2 millimetres to 3 millimetres in height]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shellSize Context triple: [Desmoulin’s whorl snail, shellSize, approximately 2 millimetres to 3 millimetres in height]
-
A.
sizeDescription
chosen
Indicates a relationship where one entity provides descriptive information about the size or scale of another entity.
-
B.
sizeStatus
Indicates the relative size condition or classification of one entity in relation to another or to a defined standard.
-
C.
bodySize
Indicates the relative physical magnitude or scale of an entity’s body, such as how large or small it is.
-
D.
shellDiameter
Indicates the diameter measurement of a shell, typically specifying the distance across it at its widest point.
-
E.
berrySize
Indicates the relative magnitude or dimensions of a berry in terms of its physical size.
- 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_69d822e4a8c08190a155df736bb7bc13 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb605f5948190ab6b20887c4b6833 |
completed | April 14, 2026, 9:47 p.m. |
| PD | Predicate disambiguation | batch_69de657c57ec8190ae0b9bb79a514566 |
completed | April 14, 2026, 4:04 p.m. |
Created at: April 10, 2026, 1:28 a.m.