Triple
T9944904
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rappaport Public Policy Fellows program |
E195179
|
entity |
| Predicate | internshipType |
P9840
|
FINISHED |
| Object | government internships |
—
|
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: government internships | Statement: [Rappaport Public Policy Fellows program, internshipType, government internships]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: internshipType Context triple: [Rappaport Public Policy Fellows program, internshipType, government internships]
-
A.
internship
chosen
Indicates that one entity is engaged in a temporary, often educational work placement or training position with another entity, typically to gain practical experience.
-
B.
summerTrainingType
Indicates the specific category or kind of training program that takes place during the summer period.
-
C.
employmentType
Indicates the specific kind or category of employment relationship that exists between an individual and an employer (e.g., full-time, part-time, contract).
-
D.
typeOfExperience
Indicates that one entity specifies the category or nature of an experience associated with another entity.
-
E.
isInterviewBased
Indicates that something (such as a study, article, or decision) is based primarily on information gathered through interviews.
- 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_69ca82e96a108190932bd1fc4acd73a0 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb61561848190aba7250f3b3c4ed5 |
completed | April 2, 2026, 12:19 a.m. |
| PD | Predicate disambiguation | batch_69cd1d97c44081908730071269f07712 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:45 p.m.