Triple
T12276690
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Customary Courts (Nigeria) |
E292606
|
entity |
| Predicate | typicalMatters |
P450
|
FINISHED |
| Object | marriage issues |
—
|
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: marriage issues | Statement: [Customary Courts (Nigeria), typicalMatters, marriage issues]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalMatters Context triple: [Customary Courts (Nigeria), typicalMatters, marriage issues]
-
A.
typicalIn
Indicates that something commonly occurs, appears, or is found within a given context, category, or environment.
-
B.
subjectMatter
chosen
Indicates the topic, theme, or content area that something (such as a work, document, or discussion) is about.
-
C.
typicalPractice
Indicates that an action, behavior, or method is commonly or customarily done in a given context or by a given group.
-
D.
typicalItem
Indicates that an item is a representative or characteristic example of a broader category, class, or set.
-
E.
typicalPrecedent
Indicates that one situation, case, or event serves as a standard or commonly followed example for how similar later situations are handled.
- 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_69d6ab6856488190b5d31178d5015f8e |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d9380a5e78819086bd4dfe9a83d1f5 |
completed | April 10, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69d91c4a66cc819083ce6fcaf5042af6 |
completed | April 10, 2026, 3:50 p.m. |
Created at: April 8, 2026, 9:52 p.m.