Triple
T14065250
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kevin Copeland |
E338451
|
entity |
| Predicate | primaryGoalInWork |
P1415
|
FINISHED |
| Object | protect the Wilson sisters |
—
|
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: protect the Wilson sisters | Statement: [Kevin Copeland, primaryGoalInWork, protect the Wilson sisters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryGoalInWork Context triple: [Kevin Copeland, primaryGoalInWork, protect the Wilson sisters]
-
A.
primaryWork
Indicates that one work is the main or most significant work associated with a given entity, as opposed to other secondary or related works.
-
B.
purposeOfWork
Indicates that one entity is the intended goal, function, or objective that motivates or justifies the work performed by another entity.
-
C.
focusesOnWork
Indicates that an entity directs its attention, effort, or primary activity toward work-related tasks or responsibilities.
-
D.
work focus
Indicates that an entity’s primary professional attention, effort, or activity is concentrated on a particular subject, task, or area.
-
E.
hasPrimaryGoal
chosen
Indicates that an entity’s main or most important objective is the specified goal.
- 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_69d81c67ba6c819091935650dfb3b895 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5689c7f48190a47ca94eaa8a9ef9 |
completed | April 14, 2026, 3 p.m. |
| PD | Predicate disambiguation | batch_69de05adef888190b023ab42ef5076b6 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:21 p.m.