Triple
T10557892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robin Cavendish |
E249135
|
entity |
| Predicate | usedMedicalDevice |
P54326
|
FINISHED |
| Object | mechanical ventilator |
—
|
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 ventilator | Statement: [Robin Cavendish, usedMedicalDevice, mechanical ventilator]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedMedicalDevice Context triple: [Robin Cavendish, usedMedicalDevice, mechanical ventilator]
-
A.
administeredWithDevice
chosen
Indicates that an action or treatment is carried out using a specific device as the means or instrument of administration.
-
B.
medicinalUse
Indicates that one entity is used as a treatment or remedy for a disease, condition, or health-related purpose affecting another entity.
-
C.
usesDrug
Indicates that an entity consumes, administers, or otherwise makes use of a specified drug.
-
D.
usedComponent
Indicates that one entity has employed or incorporated another entity as a component in its structure, function, or operation.
-
E.
usedEquipmentFrom
Indicates that one entity has utilized or operated equipment that originated from or was provided by another entity.
- 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_69d381c733c08190ab1dd6239f5f34ae |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d5271521a4819086d96e1f183ab07a |
completed | April 7, 2026, 3:47 p.m. |
| PD | Predicate disambiguation | batch_69d518fa0b4081909bffc936d78bd77b |
completed | April 7, 2026, 2:47 p.m. |
Created at: April 6, 2026, 12:35 p.m.