Triple
T23670812
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Institutional Review Board |
E584724
|
entity |
| Predicate | mayApprove |
P152920
|
FINISHED |
| Object | research protocols |
—
|
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: research protocols | Statement: [Institutional Review Board, mayApprove, research protocols]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayApprove Context triple: [Institutional Review Board, mayApprove, research protocols]
-
A.
mayReject
Indicates that one entity has the authority or option to refuse, decline, or not accept another entity or proposal.
-
B.
mayPass
Indicates that one entity is permitted or authorized to move through, cross, or gain access to another entity or location.
-
C.
mayGrant
Indicates that one entity has the authority or permission to confer, assign, or bestow a right, privilege, or resource to another entity.
-
D.
mayAdmit
Indicates that one entity has the permission or authority to allow another entity to enter, join, or be accepted into something.
-
E.
mayApply
Indicates that an entity is permitted or eligible to submit or use something (such as a rule, action, or resource) under certain conditions.
- F. None of above. chosen
Provenance (4 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_69e24901421881908c17a5293bdd4a8e |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b40ec52c8190b38a77cc3973d112 |
completed | April 29, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69f118dd13008190a8799b4e9cadbd79 |
completed | April 28, 2026, 8:30 p.m. |
| PDg | Predicate description generation | batch_69f121cc494081908c987adfcde89b0e |
completed | April 28, 2026, 9:08 p.m. |
Created at: April 17, 2026, 6:50 p.m.