Triple
T30964973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brandon Williams |
E788925
|
entity |
| Predicate | work context |
P48472
|
FINISHED |
| Object | American politics |
—
|
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: American politics | Statement: [Brandon Williams, work context, American politics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: work context Context triple: [Brandon Williams, work context, American politics]
-
A.
workWithin
Indicates that one entity performs its activities or duties inside the boundaries, scope, or context defined by another entity.
-
B.
employmentContext
Indicates the situational or organizational setting in which an employment relationship or work activity takes place.
-
C.
primaryWorkContext
chosen
Indicates the main environment, setting, or domain in which an entity typically performs its work or primary activities.
-
D.
workScope
Indicates the defined range, extent, and boundaries of tasks or responsibilities involved in a particular work activity or project.
-
E.
workWith
Indicates that one entity collaborates or engages in work-related activities together with another 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_69f224c3a6b48190951add9b7b7f0271 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6953bafb88190a860e9c68a3dd4b2 |
completed | May 3, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69f690ef92308190903a54fc74233269 |
completed | May 3, 2026, 12:03 a.m. |
Created at: April 29, 2026, 8:54 p.m.