Triple
T37277810
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ma’di language |
E924695
|
entity |
| Predicate | usedAsL2In |
P45599
|
FINISHED |
| Object | border areas of South Sudan and Uganda |
—
|
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: border areas of South Sudan and Uganda | Statement: [Ma’di language, usedAsL2In, border areas of South Sudan and Uganda]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedAsL2In Context triple: [Ma’di language, usedAsL2In, border areas of South Sudan and Uganda]
-
A.
usedAsL2With
Indicates that one entity is used as a second-level (L2) component, resource, or context together with another entity in a combined usage scenario.
-
B.
usedAsL2By
chosen
Indicates that something serves as a second language (L2) for a particular user or group of users.
-
C.
isUsedAs
Indicates that one entity serves a particular function, role, or purpose as another entity.
-
D.
usedVia
Indicates that an entity performs or achieves something by means of, or through the use of, another entity or mechanism.
-
E.
L2Is
Indicates that one entity is located at or occupies a specific level 2 (L2) position or layer relative to another entity.
- 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_69f76eacdd8c819094080d3991e6d37c |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff0214d7348190904688376df99bce |
completed | May 9, 2026, 9:44 a.m. |
| PD | Predicate disambiguation | batch_69feffd62fec8190a855922c8b3c57cf |
completed | May 9, 2026, 9:35 a.m. |
Created at: May 3, 2026, 4:16 p.m.