Triple
T3786106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | cotton gin |
E85533
|
entity |
| Predicate | effectOnSlavery |
P51496
|
FINISHED |
| Object | increased demand for enslaved labor in the American South |
—
|
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: increased demand for enslaved labor in the American South | Statement: [cotton gin, effectOnSlavery, increased demand for enslaved labor in the American South]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: effectOnSlavery Context triple: [cotton gin, effectOnSlavery, increased demand for enslaved labor in the American South]
-
A.
positionOnSlavery
Indicates a stance, opinion, or policy that an entity holds regarding the institution or practice of slavery.
-
B.
legalStatusOfSlavery
Indicates the legal condition or permissibility of slavery within a given jurisdiction, time, or context.
-
C.
historicalPeriodOfEnslavement
Indicates the specific historical period during which an entity was subjected to enslavement.
-
D.
wasEnslavedIn
Indicates that an entity was held in a state of slavery within a specified place or context.
-
E.
wasFormerlyEnslaved
Indicates that an entity was previously held in a condition of slavery or bondage but is no longer enslaved.
- 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_69aed937fa8881908208ef3801060826 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee634c6ac819099653c660c286746 |
completed | March 9, 2026, 3:24 p.m. |
| PD | Predicate disambiguation | batch_69aee3d3c92c819081d9d5c45ef37a5d |
completed | March 9, 2026, 3:14 p.m. |
| PDg | Predicate description generation | batch_69aee633dab88190b14cec8afb19ca6a |
completed | March 9, 2026, 3:24 p.m. |
Created at: March 9, 2026, 3:13 p.m.