Triple
T1569797
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | French Caribbean |
E33511
|
entity |
| Predicate | historicalSystem |
P28623
|
FINISHED |
| Object | slavery |
—
|
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: slavery | Statement: [French Caribbean, historicalSystem, slavery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalSystem Context triple: [French Caribbean, historicalSystem, slavery]
-
A.
historicalPractice
Indicates that an action, behavior, or relationship occurred as a customary or established practice during a past historical period.
-
B.
historicalForm
Indicates that one entity is an earlier or historically attested form or variant of another entity.
-
C.
historicalStatusOf
chosen
Indicates the historical condition, role, or classification that an entity held during a specific past period or context.
-
D.
historicalMethod
Indicates that a particular method, approach, or technique was used in the past, typically in a historical context or during a previous period of activity.
-
E.
historicallyBorneBy
Indicates that an entity has carried, possessed, or used another entity (such as a name, title, or symbol) at some point in the past.
- 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_69a885f11b048190935025a035302715 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a96083e7308190abbf025fe8e43abb |
completed | March 5, 2026, 10:52 a.m. |
| PD | Predicate disambiguation | batch_69a907ba63c88190b60c14dec8d1e40f |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:27 p.m.