Triple
T31710841
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sacred Heart Hospital |
E809311
|
entity |
| Predicate | attendingPhysicianCharacter |
P127445
|
FINISHED |
| Object | Perry Cox |
—
|
NE NERFINISHED |
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: Perry Cox | Statement: [Sacred Heart Hospital, attendingPhysicianCharacter, Perry Cox]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: attendingPhysicianCharacter Context triple: [Sacred Heart Hospital, attendingPhysicianCharacter, Perry Cox]
-
A.
hasDoctorCharacter
chosen
Indicates that an entity includes or features a character whose role or profession is that of a doctor.
-
B.
patientPortrayedBy
Indicates that a patient is represented or depicted by a particular actor, model, or illustrative figure.
-
C.
hasDoctorActor
Indicates that a doctor participates as an acting agent in the specified event or relationship.
-
D.
doctor
Indicates that one entity serves as a medical professional providing diagnosis, treatment, or healthcare services to another entity.
-
E.
clinicalRole
Indicates the specific function, responsibility, or position an entity holds within a clinical or healthcare context.
- 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_69f348df4e048190a4a5a9932ada78d6 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6aaf50be08190a2b62a6d881f8aee |
completed | May 3, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69f6aa20a1588190a53533fc9764efb2 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 30, 2026, 11:15 p.m.