Triple
T853848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Catholic University of America Columbus School of Law |
E18445
|
entity |
| Predicate | offersProfessionalTrainingIn |
P2858
|
FINISHED |
| Object | legal practice |
—
|
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: legal practice | Statement: [Catholic University of America Columbus School of Law, offersProfessionalTrainingIn, legal practice]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offersProfessionalTrainingIn Context triple: [Catholic University of America Columbus School of Law, offersProfessionalTrainingIn, legal practice]
-
A.
trainingFormat
Indicates the specific method or medium through which training is delivered or conducted.
-
B.
trainingInstitution
chosen
Indicates that one entity serves as the institution or organization where another entity receives training or education.
-
C.
training
Indicates that one entity is teaching, coaching, or otherwise helping another entity acquire or improve a skill, behavior, or capability.
-
D.
trainingSystem
Indicates a system or framework used to train, instruct, or develop skills or knowledge in a target entity.
-
E.
hasBeginnerFriendlyTraining
Indicates that an entity provides training or instructional resources suitable for beginners or those with little prior experience.
- 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_69a4938bdd3c8190a954a3c11844d9cf |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ac389a44819093396a58d2afa700 |
completed | March 1, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69a4aa81ef348190b067f817574e9efe |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:39 p.m.