Triple
T23518650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lissamphibia |
E574437
|
entity |
| Predicate | skinPermeability |
P48525
|
FINISHED |
| Object | highly permeable to water and gases |
—
|
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: highly permeable to water and gases | Statement: [Lissamphibia, skinPermeability, highly permeable to water and gases]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: skinPermeability Context triple: [Lissamphibia, skinPermeability, highly permeable to water and gases]
-
A.
skinCharacteristic
Indicates a relationship where an entity is associated with a particular quality, feature, or condition of its skin.
-
B.
skinThickness
Indicates the measured thickness of an entity’s skin, typically quantifying how thick its outer tissue layer is.
-
C.
permeability
chosen
Indicates how easily a substance, material, or barrier allows another substance (such as a fluid, gas, or signal) to pass through it.
-
D.
effectOnSkin
Indicates the impact or influence that something has on the condition, appearance, or health of skin.
-
E.
skinContactSuitability
Indicates that one entity is suitable, safe, or appropriate for direct contact with the skin of another entity.
- 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_69e245bb3dcc8190ba9a2b35972b58d0 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1aa83c538819096bc548e3e0ddbd0 |
completed | April 29, 2026, 6:51 a.m. |
| PD | Predicate disambiguation | batch_69f0621165c08190a0b27b1319733959 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 6:08 p.m.