Triple
T50985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman-Dutch law |
E999
|
entity |
| Predicate | retainedIn |
P1393
|
FINISHED |
| Object | South African legal system |
—
|
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: South African legal system | Statement: [Roman-Dutch law, retainedIn, South African legal system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: retainedIn Context triple: [Roman-Dutch law, retainedIn, South African legal system]
-
A.
includes
chosen
Indicates that one entity contains, encompasses, or has another entity as a part, member, or subset.
-
B.
protectedIn
Indicates that one entity is safeguarded, preserved, or kept safe within the context, environment, or jurisdiction of another entity.
-
C.
holding
Indicates that one entity is physically grasping, carrying, or keeping another entity in its possession or control.
-
D.
reserves
Indicates that an entity has arranged in advance to hold or secure something for future use or access.
-
E.
retired
Indicates that an entity has permanently stopped working in their former occupation or role, typically after reaching a certain age or service duration.
- 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_69a2480baefc81909951b14058479aa2 |
completed | Feb. 28, 2026, 1:42 a.m. |
| NER | Named-entity recognition | batch_69a24ba7016481909d595402712db6e2 |
completed | Feb. 28, 2026, 1:57 a.m. |
| PD | Predicate disambiguation | batch_69a24ac23f04819080cef9365ed990d4 |
completed | Feb. 28, 2026, 1:54 a.m. |
Created at: Feb. 28, 2026, 1:47 a.m.