Triple
T1337842
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvard teaching hospitals |
E28793
|
entity |
| Predicate | hasTypeOfTrainingProgram |
P24513
|
FINISHED |
| Object | medical residency programs |
—
|
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: medical residency programs | Statement: [Harvard teaching hospitals, hasTypeOfTrainingProgram, medical residency programs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypeOfTrainingProgram Context triple: [Harvard teaching hospitals, hasTypeOfTrainingProgram, medical residency programs]
-
A.
hasTrainingType
chosen
Indicates that an entity is associated with or characterized by a specific type or category of training.
-
B.
hasEducationalProgram
Indicates that an entity offers, runs, or is associated with a specific educational program.
-
C.
hasProgramme
Indicates that an entity is associated with or offers a particular programme (such as a course of study, plan, or structured set of activities).
-
D.
hasBeginnerFriendlyTraining
Indicates that an entity provides training or instructional resources suitable for beginners or those with little prior experience.
-
E.
hasOnlinePrograms
Indicates that an entity offers or provides programs, courses, or services that are available online.
- 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_69a498561a508190a3e1bc137c2b866a |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c2115d388190b031ae2de1296f8a |
completed | March 1, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69a4bef174708190a07bbc697fe19a2d |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:55 p.m.