Triple
T4160760
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kocher forceps |
E91526
|
entity |
| Predicate | clinicalRole |
P54174
|
FINISHED |
| Object | mechanical aid in achieving hemostasis |
—
|
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: mechanical aid in achieving hemostasis | Statement: [Kocher forceps, clinicalRole, mechanical aid in achieving hemostasis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: clinicalRole Context triple: [Kocher forceps, clinicalRole, mechanical aid in achieving hemostasis]
-
A.
primaryPractitioners
Indicates the entities that are the main or most directly responsible practitioners of a given activity, field, or practice in relation to another entity.
-
B.
healthcareType
Indicates the category or kind of healthcare service, system, or coverage associated with an entity.
-
C.
professionServed
Indicates that an entity has performed work or provided services in a particular profession or occupational role.
-
D.
positionOnHealthCare
Indicates a person or entity’s stance, opinion, or policy preference regarding health care systems, services, or reforms.
-
E.
clinicalSignOf
Indicates that one clinical sign is evidence or manifestation of a particular disease, condition, or underlying medical state.
- F. None of above. chosen
Provenance (4 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_69aed9626ebc8190a39de631788bea3e |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af0321eee88190871c1d4bf44a5007 |
completed | March 9, 2026, 5:28 p.m. |
| PD | Predicate disambiguation | batch_69af018dc90c8190a754b1bfbc802e80 |
completed | March 9, 2026, 5:21 p.m. |
| PDg | Predicate description generation | batch_69af0320775c8190b90d80f512060f1c |
completed | March 9, 2026, 5:28 p.m. |
Created at: March 9, 2026, 3:44 p.m.