Triple
T14707556
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Veronica Donovan |
E345464
|
entity |
| Predicate | professionRole |
P2374
|
FINISHED |
| Object | defense attorney |
—
|
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: defense attorney | Statement: [Veronica Donovan, professionRole, defense attorney]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: professionRole Context triple: [Veronica Donovan, professionRole, defense attorney]
-
A.
employedRole
Indicates that an entity holds or performs a specific role or position within an employment or work context.
-
B.
roleDuringOccupation
Indicates the specific role or position an entity held during a particular occupation or period of control.
-
C.
subjectOccupation
chosen
Indicates that the subject holds or performs a particular job, profession, or role as their occupation.
-
D.
professionalCategory
Indicates the classification of an entity according to its professional field, role, or occupational domain.
-
E.
natureOfOccupation
Indicates the type or character of a person's occupation, describing what kind of work or role it is rather than who performs it.
- 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_69d822e4a8c08190a155df736bb7bc13 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb609965081908f654bcb9eaaa145 |
completed | April 14, 2026, 9:47 p.m. |
| PD | Predicate disambiguation | batch_69de657c57ec8190ae0b9bb79a514566 |
completed | April 14, 2026, 4:04 p.m. |
Created at: April 10, 2026, 1:28 a.m.