Triple
T34105578
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mpongwe people |
E874696
|
entity |
| Predicate | roleInSlaveTrade |
P202782
|
FINISHED |
| Object | intermediary traders in Atlantic networks |
—
|
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: intermediary traders in Atlantic networks | Statement: [Mpongwe people, roleInSlaveTrade, intermediary traders in Atlantic networks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInSlaveTrade Context triple: [Mpongwe people, roleInSlaveTrade, intermediary traders in Atlantic networks]
-
A.
wasEnslavedIn
Indicates that an entity was held in a state of slavery within a specified place or context.
-
B.
usesSlavery
Indicates that an entity employs or relies on enslaved people or forced labor as part of its operations or activities.
-
C.
enslavedAsChild
Indicates that an individual was forced into slavery during their childhood.
-
D.
populationGroupEnslaved
Indicates that one population group is held in a condition of slavery or forced servitude by another.
-
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_69f349a80d4481908527317d43f5c579 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a00b8e0a5508190abc5c1e492bed12e |
completed | May 10, 2026, 4:57 p.m. |
| PD | Predicate disambiguation | batch_6a00b8327d048190850af317f60f0f8b |
completed | May 10, 2026, 4:54 p.m. |
| PDg | Predicate description generation | batch_6a00b8dfde3c81908c04ceccf67329db |
completed | May 10, 2026, 4:57 p.m. |
Created at: May 1, 2026, 1:53 a.m.