Triple
T699713
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Black Codes |
E13970
|
entity |
| Predicate | required |
P100
|
FINISHED |
| Object | labor contracts for African American workers |
—
|
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: labor contracts for African American workers | Statement: [Black Codes, required, labor contracts for African American workers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: required Context triple: [Black Codes, required, labor contracts for African American workers]
-
A.
requires
chosen
Indicates that one entity must exist, occur, or be satisfied before another entity can exist, occur, or be carried out.
-
B.
requiredBy
Indicates that one entity depends on or cannot function properly without another entity being present, completed, or satisfied.
-
C.
demanded
Indicates that one entity forcefully or insistently requested something from another entity.
-
D.
requiredInformation
Indicates that certain data or details are necessary and must be provided for a process, action, or relationship to proceed or be valid.
-
E.
requiresDispositionOf
Indicates that one entity must be appropriately handled, removed, or otherwise disposed of as a condition related to another entity or situation.
- 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_69a493406c408190957eeec9048a8fb6 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a0dd4afc81909e4e869356006f33 |
completed | March 1, 2026, 8:26 p.m. |
| PD | Predicate disambiguation | batch_69a49d265cf08190877f920d52a5ba43 |
completed | March 1, 2026, 8:10 p.m. |
Created at: March 1, 2026, 7:36 p.m.