Triple
T27028222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Post-9/11 GI Bill |
E680846
|
entity |
| Predicate | bookStipendBasedOn |
P162031
|
FINISHED |
| Object | enrollment and benefit percentage |
—
|
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: enrollment and benefit percentage | Statement: [Post-9/11 GI Bill, bookStipendBasedOn, enrollment and benefit percentage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bookStipendBasedOn Context triple: [Post-9/11 GI Bill, bookStipendBasedOn, enrollment and benefit percentage]
-
A.
bookStipendMaximumPerYear
Indicates the maximum amount of stipend funding that can be allocated for books within a single year.
-
B.
bookSelection
Indicates the act or result of choosing a particular book from a set of available options.
-
C.
containsBook
Indicates that one entity (typically a container or collection) includes a specific book as part of its contents.
-
D.
intendedNumberOfBooks
Indicates the number of books that an agent plans or aims to have, produce, read, or otherwise be associated with, as opposed to the number actually realized.
-
E.
book4Subject
Indicates that something is the subject or topic that a particular book is about.
- 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_69eeeb5566f08190813daf896fa3da04 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f622abdfac8190988421c946411d7e |
completed | May 2, 2026, 4:13 p.m. |
| PD | Predicate disambiguation | batch_69f620e0b37481909a280574decbd443 |
completed | May 2, 2026, 4:05 p.m. |
| PDg | Predicate description generation | batch_69f621c7d3e0819095b1f327637ae4f9 |
completed | May 2, 2026, 4:09 p.m. |
Created at: April 27, 2026, 7:12 a.m.