Triple
T28532433
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Office for Human Research Protections |
E722077
|
entity |
| Predicate | areaOfRegulation |
P63323
|
FINISHED |
| Object | biomedical human subjects research |
—
|
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: biomedical human subjects research | Statement: [Office for Human Research Protections, areaOfRegulation, biomedical human subjects research]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: areaOfRegulation Context triple: [Office for Human Research Protections, areaOfRegulation, biomedical human subjects research]
-
A.
regulatesArea
Indicates that one entity exercises control or governance over the spatial extent, scope, or domain of another entity.
-
B.
regulatedArea
chosen
Indicates that an area is subject to specific rules, controls, or restrictions imposed by an authority.
-
C.
areaDefinedAs
Indicates that one area is formally specified, delimited, or characterized in terms of another area or defining criteria.
-
D.
regionRuled
Indicates that a particular region is governed or controlled by a specified ruler or authority.
-
E.
areaOfAuthority
Indicates the domain, region, or scope within which an entity has official power, control, or responsibility.
- 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_69f01a5d7ec88190ada2d5be7c06c35d |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f6617ba4a88190bfc5c305acb4f93f |
completed | May 2, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69f660f082508190a95a7888ad66cb2e |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 28, 2026, 3:29 a.m.