Triple
T9113436
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prasanna Puwanarajah |
E218660
|
entity |
| Predicate | transitionedFromCareer |
P71077
|
FINISHED |
| Object | medicine |
—
|
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: medicine | Statement: [Prasanna Puwanarajah, transitionedFromCareer, medicine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transitionedFromCareer Context triple: [Prasanna Puwanarajah, transitionedFromCareer, medicine]
-
A.
managedCareerOf
Indicates that one entity was responsible for overseeing, directing, or handling the professional career of another entity.
-
B.
occupationalChange
chosen
Indicates a change in a person’s job, profession, or occupational status over time.
-
C.
partOfCareer
Indicates that one entity represents a role, position, or period that forms a component or phase within another entity’s overall career.
-
D.
laterCareer
Indicates that the associated information or events pertain to a later stage or phase in an entity’s professional life or career trajectory.
-
E.
careerStart
Indicates the point in time when an entity begins its professional career or main occupational activity.
- 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_69ca83dc94ac8190b9ef42684d36ff39 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca84b0a048190964f560f78e27cce |
completed | April 1, 2026, 5:08 a.m. |
| PD | Predicate disambiguation | batch_69cc65fe5be081909d4470d6317b14a6 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:16 p.m.