Triple
T7027846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UNC School of Science and Mathematics |
E163192
|
entity |
| Predicate | studentSelection |
P19222
|
FINISHED |
| Object | academically gifted 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: academically gifted students | Statement: [UNC School of Science and Mathematics, studentSelection, academically gifted students]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: studentSelection Context triple: [UNC School of Science and Mathematics, studentSelection, academically gifted students]
-
A.
drawsStudentsFrom
chosen
Indicates that an institution or program attracts and enrolls students originating from a particular source, place, or group.
-
B.
academicSelection
Indicates a relationship where an entity chooses or designates another entity for an academic purpose, role, or opportunity.
-
C.
studentSection
Indicates a relationship where a student is enrolled in or associated with a particular course section.
-
D.
selectionProcess
Indicates the procedure or set of steps by which one or more options are evaluated and chosen from a larger set of candidates.
-
E.
studentComposition
Indicates that one entity is composed of or consists of students, specifying a part-whole relationship where students collectively form the other 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_69c6885d691c81908cf7d31083113886 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e458ad9c81908c3f492b317ce291 |
completed | March 27, 2026, 8:11 p.m. |
| PD | Predicate disambiguation | batch_69c6e1b9a2488190aea351d96afa5a12 |
completed | March 27, 2026, 7:59 p.m. |
Created at: March 27, 2026, 2:35 p.m.