Triple
T2316792
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St. John’s College, Annapolis |
E51082
|
entity |
| Predicate | usesTeachingMethod |
P24055
|
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: [St. John’s College, Annapolis, usesTeachingMethod, Socratic seminar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesTeachingMethod Context triple: [St. John’s College, Annapolis, usesTeachingMethod, Socratic seminar]
-
A.
typeOfTeaching
chosen
Indicates the specific method or style of teaching used in an instructional context.
-
B.
hasTeaching
Indicates that one entity provides instruction or educational guidance to another entity.
-
C.
coreTeaching
Indicates that an entity serves as a primary or foundational teaching or instructional activity for another entity.
-
D.
usesCurriculum
Indicates that one entity adopts or applies a particular curriculum as the basis for its instruction, training, or educational activities.
-
E.
hasTeachingRole
Indicates that one entity holds a position or responsibility involving teaching or instruction in relation to another 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_69a88b074b908190ae983dbca7757d88 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abc685f05481909c863b29d1f6bacd |
completed | March 7, 2026, 6:32 a.m. |
| PD | Predicate disambiguation | batch_69abc58e88e481908733fdf79d3f8a15 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:49 p.m.