Triple
T28459993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brooklyn Latin School |
E720123
|
entity |
| Predicate | instructionalApproach |
P779
|
FINISHED |
| Object | Socratic seminar |
—
|
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: Socratic seminar | Statement: [Brooklyn Latin School, instructionalApproach, Socratic seminar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: instructionalApproach Context triple: [Brooklyn Latin School, instructionalApproach, Socratic seminar]
-
A.
educationalApproach
chosen
Indicates the method, strategy, or philosophy used to guide teaching and learning within an educational context.
-
B.
typeOfTeaching
Indicates the specific method or style of teaching used in an instructional context.
-
C.
coreTeaching
Indicates that an entity serves as a primary or foundational teaching or instructional activity for another entity.
-
D.
teachingPhilosophy
Indicates a relationship where an educator’s guiding beliefs, values, and principles about how teaching and learning should occur are expressed or characterized.
-
E.
academicApproach
Indicates an entity’s characteristic method, strategy, or style used in academic work, study, or instruction.
- 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_69f01a58a67c819097936d9e8da8d6e6 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f65876c52c8190bc889c7a67bd07f3 |
completed | May 2, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 2:38 a.m.