Triple
T15030733
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Office of Justice Assistance, Research, and Statistics |
E378335
|
entity |
| Predicate | typeOfGrantAdministered |
P89440
|
FINISHED |
| Object | criminal justice grants |
—
|
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: criminal justice grants | Statement: [Office of Justice Assistance, Research, and Statistics, typeOfGrantAdministered, criminal justice grants]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfGrantAdministered Context triple: [Office of Justice Assistance, Research, and Statistics, typeOfGrantAdministered, criminal justice grants]
-
A.
typeOfGrant
Indicates the specific category or kind of grant associated with an entity.
-
B.
typeOfGrantManaged
chosen
Indicates that one entity manages or administers a specific type or category of grant in relation to another entity or context.
-
C.
granteeType
Indicates the classification or category of the entity that receives a grant or is granted a right, benefit, or permission.
-
D.
grantType
Indicates the specific authorization or credential flow used to obtain access or permissions in a grant-based process.
-
E.
typeOfAdministration
Indicates the specific form or system of administration applied to or governing an entity.
- 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_69d85cd46b2c819090d054c27787f677 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded7e2416081908dfba48d7f7b4a84 |
completed | April 15, 2026, 12:12 a.m. |
| PD | Predicate disambiguation | batch_69de9a67cbc481909c19c2de57de4eb7 |
completed | April 14, 2026, 7:50 p.m. |
Created at: April 10, 2026, 2:59 a.m.