Triple
T23154053
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Craig Cunningham |
E578393
|
entity |
| Predicate | consequenceOfMedicalEvent |
P812
|
FINISHED |
| Object | partial amputation of left leg |
—
|
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: partial amputation of left leg | Statement: [Craig Cunningham, consequenceOfMedicalEvent, partial amputation of left leg]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: consequenceOfMedicalEvent Context triple: [Craig Cunningham, consequenceOfMedicalEvent, partial amputation of left leg]
-
A.
hasConsequence
chosen
Indicates that one event, action, or condition leads to or results in another as its outcome or effect.
-
B.
consequenceOfInfluence
Indicates that one event, state, or condition occurs as a result of the influence or impact exerted by another.
-
C.
consequenceInText
Indicates that one event, action, or state is presented in the text as a consequence or result of another.
-
D.
medicalEvent
Indicates that a specific health-related occurrence or clinical incident has taken place involving one or more entities.
-
E.
significantEventConsequence
Indicates that one event leads to an important or impactful consequence for another event, state, or 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_69e245fb8de081908f0eba7b5fd75bc4 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18efbe9a08190bcb6e822b8eab544 |
completed | April 29, 2026, 4:54 a.m. |
| PD | Predicate disambiguation | batch_69ef89ff76808190808ee4ad9dea776b |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:01 p.m.