Triple
T230730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Proton Synchrotron |
E4404
|
entity |
| Predicate | roleInComplex |
P268
|
FINISHED |
| Object | proton injector |
—
|
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: proton injector | Statement: [Proton Synchrotron, roleInComplex, proton injector]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInComplex Context triple: [Proton Synchrotron, roleInComplex, proton injector]
-
A.
roleInvolves
Indicates that a particular role includes or requires participation in a specified activity, responsibility, or function.
-
B.
role
chosen
Indicates the function, position, or responsibility that one entity holds in relation to another within a given context.
-
C.
deFactoRole
Indicates that an entity effectively functions in a role or capacity in practice, even if that role is not formally or officially assigned.
-
D.
roleInEcosystem
Indicates the specific function or contribution an entity has within an ecosystem and how it interacts with other components of that system.
-
E.
typeOfRole
Indicates that one entity specifies the kind or category of role that another entity holds or performs.
- 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_69a257363ffc81909757bde7ab3404da |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25e0868708190ad551ca06cc57f4a |
completed | Feb. 28, 2026, 3:16 a.m. |
| PD | Predicate disambiguation | batch_69a25b5a075081909b0e9b88c1492d5a |
completed | Feb. 28, 2026, 3:04 a.m. |
Created at: Feb. 28, 2026, 2:53 a.m.