Triple
T10610044
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gi protein |
E275980
|
entity |
| Predicate | canBeInhibitedBy |
P93780
|
FINISHED |
| Object | pertussis toxin |
—
|
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: pertussis toxin | Statement: [Gi protein, canBeInhibitedBy, pertussis toxin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canBeInhibitedBy Context triple: [Gi protein, canBeInhibitedBy, pertussis toxin]
-
A.
canBeDisabledOn
Indicates that a feature, function, or capability has the property that it can be turned off or deactivated when applied to the referenced entity.
-
B.
canBeSuppressedBy
chosen
Indicates that one entity has the ability to reduce, inhibit, or nullify the effect, presence, or activity of another entity.
-
C.
isProhibitedFor
Indicates that a certain action, object, or condition is not allowed or is forbidden for a specified entity or group.
-
D.
isPreventableBy
Indicates that the occurrence or effect of one entity can be avoided or stopped through the action, intervention, or influence of another entity.
-
E.
inhibits
Indicates that one entity prevents, restrains, or reduces the activity, effect, or occurrence 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_69d6aaf948d88190806cc3a8c47a3fb2 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d6df59468881909b0c67d3f08c4b76 |
completed | April 8, 2026, 11:06 p.m. |
| PD | Predicate disambiguation | batch_69d6dd7a223c8190854409d76368f3e8 |
completed | April 8, 2026, 10:58 p.m. |
Created at: April 8, 2026, 7:32 p.m.