Triple
T22465145
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Native Hawaiian Housing Block Grant Program |
E555332
|
entity |
| Predicate | programDesign |
P148316
|
FINISHED |
| Object | formula-based block grant |
—
|
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: formula-based block grant | Statement: [Native Hawaiian Housing Block Grant Program, programDesign, formula-based block grant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: programDesign Context triple: [Native Hawaiian Housing Block Grant Program, programDesign, formula-based block grant]
-
A.
programming
Indicates that an entity writes, develops, or modifies software or code, typically using a programming language to create or control computer programs.
-
B.
designCode
Indicates that one entity creates, specifies, or defines the design or coding scheme used by another entity.
-
C.
programDesignation
Indicates that an entity is assigned or identified by a specific program designation or label.
-
D.
program
Indicates that an entity creates, writes, or develops a computer program or software application.
-
E.
programGeneration
Indicates that one entity creates, writes, or produces a program (such as software or code) for or on behalf of another entity.
- 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_69e11e51fdec8190adfdf9f8a6362221 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15b82549c8190943c0940bb90bafc |
completed | April 29, 2026, 1:14 a.m. |
| PD | Predicate disambiguation | batch_69e898b6eee08190ba673a0ee329e671 |
completed | April 22, 2026, 9:45 a.m. |
| PDg | Predicate description generation | batch_69e8aa39e3388190b659d59948ebf3e6 |
completed | April 22, 2026, 11 a.m. |
Created at: April 16, 2026, 8:48 p.m.