Triple
T23495728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Legal Information Institute |
E571699
|
entity |
| Predicate | operatesOnModel |
P53103
|
FINISHED |
| Object | open access |
—
|
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: open access | Statement: [Legal Information Institute, operatesOnModel, open access]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesOnModel Context triple: [Legal Information Institute, operatesOnModel, open access]
-
A.
operatesOnProperty
Indicates that one entity performs an action or has an effect specifically targeting a particular property or attribute of another entity.
-
B.
operatesOnPropertyOf
Indicates that an action or process is applied specifically to a property or attribute of an entity, rather than to the entity itself.
-
C.
operatesOnLayer
Indicates that an entity performs actions or functions specifically targeting a particular layer within a layered structure or system.
-
D.
definesOperationOn
Indicates that one entity specifies or establishes the operation that is applied to another entity.
-
E.
appliesModel
chosen
Indicates that one entity uses or executes a specific model on another entity or data set.
- 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_69e245b4829881909b77a70e942bbd54 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a7e00384819092729319a378d4ab |
completed | April 29, 2026, 6:40 a.m. |
| PD | Predicate disambiguation | batch_69f0621165c08190a0b27b1319733959 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 6:05 p.m.