Triple
T29537978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Experience Corps |
E749402
|
entity |
| Predicate | evaluationShows |
P21543
|
FINISHED |
| Object | improved reading skills for participating students |
—
|
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: improved reading skills for participating students | Statement: [Experience Corps, evaluationShows, improved reading skills for participating students]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: evaluationShows Context triple: [Experience Corps, evaluationShows, improved reading skills for participating students]
-
A.
showsThat
chosen
Indicates that one entity demonstrates, proves, or provides evidence for the truth or validity of another.
-
B.
evaluationAspect
Indicates the specific dimension or criterion of performance or quality that is being assessed within an evaluation.
-
C.
ultimatelyShows
Indicates that something eventually reveals, demonstrates, or makes clear another thing as a final outcome or conclusion.
-
D.
evaluationModel
Indicates a relationship where one entity serves as a model, standard, or framework used to assess, judge, or measure the performance or quality of another entity.
-
E.
evaluationUse
Indicates that something is used as a basis, tool, or resource for evaluating or assessing something else.
- 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_69f0bd47abb081909bd6e6a33d770fd8 |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f66cc8f3b481909d2c65c0acffb2ad |
completed | May 2, 2026, 9:29 p.m. |
| PD | Predicate disambiguation | batch_69f6659d36208190b01412600a4ed57d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 5 p.m.