Triple
T27077881
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | D.O. |
E685511
|
entity |
| Predicate | requiresLicensingExams |
P9144
|
FINISHED |
| Object |
COMLEX-USA
COMLEX-USA is a comprehensive series of national board examinations that assess the medical knowledge and clinical skills of osteopathic physicians in the United States for licensure.
|
E1753826
|
NE FINISHED |
How this triple was built (3 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: COMLEX-USA | Statement: [D.O., requiresLicensingExams, COMLEX-USA]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: COMLEX-USA Triple: [D.O., requiresLicensingExams, COMLEX-USA]
Generated description
COMLEX-USA is a comprehensive series of national board examinations that assess the medical knowledge and clinical skills of osteopathic physicians in the United States for licensure.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: requiresLicensingExams Context triple: [D.O., requiresLicensingExams, COMLEX-USA]
-
A.
requiresCertification
Indicates that one entity can only be performed, accessed, or considered valid if another entity has an appropriate certification.
-
B.
writtenExamRequiredBefore
Indicates that completing a written exam is a prerequisite that must occur before another specified action or event.
-
C.
requiresLicenseForPractice
chosen
Indicates that engaging in the specified professional practice is legally contingent upon holding a valid license.
-
D.
requiresQualificationStandard
Indicates that performing or engaging in the referenced activity, role, or process is contingent upon meeting a specified qualification standard.
-
E.
requiresPractice
Indicates that performing or mastering one entity depends on engaging in repeated practice or training involving another entity.
- F. None of above.
Provenance (6 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_69ef14843b1481909d828b3d5a44550a |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f7b2f3a104819098ddd8909eaf596c |
completed | May 3, 2026, 8:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a123ade1d588190bcc5c6a2af556ef9 |
completed | May 23, 2026, 11:40 p.m. |
| NEDg | Description generation | batch_6a123baa5c608190908cb92bee2e9cb2 |
completed | May 23, 2026, 11:43 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a123c6a4e4481908d79c547106ba5f0 |
completed | May 23, 2026, 11:46 p.m. |
| PD | Predicate disambiguation | batch_69f7b1b8a9fc8190a1279e67a2d12707 |
completed | May 3, 2026, 8:36 p.m. |
Created at: April 27, 2026, 8:32 a.m.