Triple
T3781305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sudanese |
E85421
|
entity |
| Predicate | cultureIncludes |
P37177
|
FINISHED |
| Object | Sudanese cuisine |
—
|
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: Sudanese cuisine | Statement: [Sudanese, cultureIncludes, Sudanese cuisine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cultureIncludes Context triple: [Sudanese, cultureIncludes, Sudanese cuisine]
-
A.
culturalCategory
Indicates that one entity classifies or groups another entity according to a particular culture, tradition, or culturally defined type.
-
B.
cultureMedium
Indicates the substance or environment used to grow, maintain, or study a biological specimen or culture.
-
C.
culturePractice
Indicates a relationship where a group or society engages in, maintains, or performs a particular cultural activity, custom, or tradition.
-
D.
culturalSphere
Indicates that one entity belongs to, is influenced by, or participates in the cultural domain, tradition, or milieu defined by another entity.
-
E.
culturalHeritageIncludes
chosen
Indicates that a cultural heritage entity encompasses, contains, or incorporates another cultural element, tradition, artifact, or practice as part of its overall heritage.
- 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_69aed937fa8881908208ef3801060826 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee634c6ac819099653c660c286746 |
completed | March 9, 2026, 3:24 p.m. |
| PD | Predicate disambiguation | batch_69aee3d3c92c819081d9d5c45ef37a5d |
completed | March 9, 2026, 3:14 p.m. |
Created at: March 9, 2026, 3:12 p.m.