Triple
T925547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patrick Bouvier Kennedy |
E19973
|
entity |
| Predicate | receivedTreatment |
P4714
|
FINISHED |
| Object | hyperbaric oxygen therapy |
—
|
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: hyperbaric oxygen therapy | Statement: [Patrick Bouvier Kennedy, receivedTreatment, hyperbaric oxygen therapy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: receivedTreatment Context triple: [Patrick Bouvier Kennedy, receivedTreatment, hyperbaric oxygen therapy]
-
A.
treatment
chosen
Indicates that one entity is used as a medical or therapeutic intervention to address, manage, or cure a condition affecting another entity.
-
B.
treats
Indicates that one entity provides medical care or therapeutic intervention to another entity.
-
C.
hasSurgery
Indicates that a surgical procedure is performed on or undergone by an entity.
-
D.
underwent
Indicates that an entity experienced or was subjected to a process, event, or change, typically as the patient of an action.
-
E.
hasDischarge
Indicates that one entity releases, emits, or expels a substance, energy, or flow from itself.
- 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_69a493a099788190a696d9d8408cbaf4 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b388f0bc8190a087222636135ba5 |
completed | March 1, 2026, 9:45 p.m. |
| PD | Predicate disambiguation | batch_69a4b2970a4c8190b22cb2fd4706f62b |
completed | March 1, 2026, 9:41 p.m. |
Created at: March 1, 2026, 7:40 p.m.