Triple
T26326281
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Philosophy and Opinions of Marcus Garvey |
E662260
|
entity |
| Predicate | compilerRelationship |
P160248
|
FINISHED |
| Object | spouse of Marcus Garvey |
—
|
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: spouse of Marcus Garvey | Statement: [Philosophy and Opinions of Marcus Garvey, compilerRelationship, spouse of Marcus Garvey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: compilerRelationship Context triple: [Philosophy and Opinions of Marcus Garvey, compilerRelationship, spouse of Marcus Garvey]
-
A.
relatedWorkOfCompiler
Indicates that one work is associated with or connected to the compiler of another work, typically through authorship, contribution, or editorial involvement.
-
B.
compilerType
Indicates the specific kind or category of compiler associated with or used by an entity.
-
C.
compilerLanguage
Indicates that one entity is the programming language in which a given compiler is implemented.
-
D.
compilerOccupation
Indicates that one entity works as a compiler (e.g., of texts, data, or code) in relation to another entity, typically an organization, project, or work.
-
E.
compiler
Indicates that one entity serves as a compiler of another, typically transforming source material (such as code or documents) into a compiled or aggregated form.
- F. None of above. chosen
Provenance (4 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_69ee812f32748190871d970c4e2a8ddf |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f60f2fec2c8190a0271e3256f22be6 |
completed | May 2, 2026, 2:50 p.m. |
| PD | Predicate disambiguation | batch_69f5f7ff548c8190a23e98c5e66e0bc7 |
completed | May 2, 2026, 1:11 p.m. |
| PDg | Predicate description generation | batch_69f5ffc6268c8190b63f6360ebadab73 |
completed | May 2, 2026, 1:44 p.m. |
Created at: April 26, 2026, 10:31 p.m.