Triple
T7073848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern African Customs Union |
E164764
|
entity |
| Predicate | hasAcronymPronunciation |
P43870
|
FINISHED |
| Object | saku |
—
|
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: saku | Statement: [Southern African Customs Union, hasAcronymPronunciation, saku]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAcronymPronunciation Context triple: [Southern African Customs Union, hasAcronymPronunciation, saku]
-
A.
hasPronunciationDifferenceFrom
Indicates that two linguistic items differ in how they are pronounced.
-
B.
hasCommonAcronymUsage
Indicates that two terms share the same commonly used acronym in practice.
-
C.
isMorePronouncedIn
Indicates that a particular feature, quality, or effect appears with greater intensity or prominence in one context, entity, or condition than in another.
-
D.
hasExampleWordPronunciation
Indicates that an entity is associated with a specific example of how a word is pronounced.
-
E.
hasAcronymExpansionLanguage
chosen
Indicates that a specified language is the language in which an acronym’s full expansion is expressed.
- 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_69c6887b96548190a8a9b3ac8adf4119 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e4ccb42c81909f5627aa97db7a84 |
completed | March 27, 2026, 8:13 p.m. |
| PD | Predicate disambiguation | batch_69c6e1bfcb948190a5ada74fb8c054cb |
completed | March 27, 2026, 8 p.m. |
Created at: March 27, 2026, 2:39 p.m.