Triple
T11880297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dutch Tobago |
E282640
|
entity |
| Predicate | controlPattern |
P38740
|
FINISHED |
| Object | periodically controlled by the Dutch West India Company |
—
|
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: periodically controlled by the Dutch West India Company | Statement: [Dutch Tobago, controlPattern, periodically controlled by the Dutch West India Company]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: controlPattern Context triple: [Dutch Tobago, controlPattern, periodically controlled by the Dutch West India Company]
-
A.
kitPattern
Indicates the design or visual pattern featured on a team's kit or uniform.
-
B.
operatingPattern
Indicates the characteristic way in which an entity functions or operates over time, such as its typical mode, schedule, or behavioral pattern.
-
C.
controlFrom
chosen
Indicates that one entity exercises authority, influence, or regulatory power over another entity or process.
-
D.
controlMethods
Indicates the methods or techniques used by one entity to direct, regulate, or influence the behavior, operation, or state of another entity.
-
E.
maskPattern
Indicates a relationship where one entity serves as a masking template or pattern that determines which parts or aspects of another entity are revealed, hidden, or transformed.
- 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_69d6ab2945d081908a5851c916cbcfb5 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8d39d2934819093b9f7006f45e5cb |
completed | April 10, 2026, 10:40 a.m. |
| PD | Predicate disambiguation | batch_69d8bb272f88819090c37c944c5a60ab |
completed | April 10, 2026, 8:56 a.m. |
Created at: April 8, 2026, 9:44 p.m.