Triple
T29154792
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reactome pathways |
E739006
|
entity |
| Predicate | supportsInferredEventsFor |
P85259
|
FINISHED |
| Object | model organisms |
—
|
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: model organisms | Statement: [Reactome pathways, supportsInferredEventsFor, model organisms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsInferredEventsFor Context triple: [Reactome pathways, supportsInferredEventsFor, model organisms]
-
A.
supportsInferenceOf
chosen
Indicates that one entity provides a logical basis or justification for concluding or deriving another entity.
-
B.
supportedEvent
Indicates that an entity is capable of recognizing, handling, or being associated with a particular type of event.
-
C.
isSupportedFor
Indicates that one entity provides compatibility, assistance, or backing necessary for another entity’s proper use or operation.
-
D.
supportedIn
Indicates that one entity is valid, applicable, or functionally enabled within the context, environment, platform, or scope defined by another entity.
-
E.
supportsEventSeries
Indicates that an entity provides the necessary functionality or resources to host, manage, or accommodate a recurring series of related events.
- 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_69f07cb46f148190874eb8576a447567 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_6a030c7d03308190a102689db1e8b657 |
completed | May 12, 2026, 11:18 a.m. |
| PD | Predicate disambiguation | batch_6a030a57b16c81909191270f64a77fcf |
completed | May 12, 2026, 11:09 a.m. |
Created at: April 28, 2026, 11:44 a.m.