Triple
T10086124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ignicoccus hospitalis |
E215224
|
entity |
| Predicate | outerMembrane |
P56101
|
FINISHED |
| Object | energized outer cellular membrane |
—
|
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: energized outer cellular membrane | Statement: [Ignicoccus hospitalis, outerMembrane, energized outer cellular membrane]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: outerMembrane Context triple: [Ignicoccus hospitalis, outerMembrane, energized outer cellular membrane]
-
A.
outerSurface
chosen
Indicates that one entity forms the external boundary or outermost layer of another entity.
-
B.
cellWallContainsPeptidoglycan
Indicates that the cell wall of an organism includes peptidoglycan as one of its structural components.
-
C.
cellWallComponent
Indicates that one entity is a molecular or structural component of the cell wall of the other entity.
-
D.
hasTransmembraneDomains
Indicates that an entity (typically a protein) possesses one or more regions that span across a biological membrane.
-
E.
membraneLipidType
Indicates the specific type or class of lipid that composes or is associated with a membrane.
- 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_69ca83a1eed081908b2e9580f2ebeea7 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdd04609748190987a9364a387fa61 |
completed | April 2, 2026, 2:11 a.m. |
| PD | Predicate disambiguation | batch_69cd4b97870481908f7a89df10d58a9e |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:01 p.m.