Triple
T25688924
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bantu zone U |
E644145
|
entity |
| Predicate | hasSubgroupingUnit |
P47820
|
FINISHED |
| Object | language group |
—
|
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: language group | Statement: [Bantu zone U, hasSubgroupingUnit, language group]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSubgroupingUnit Context triple: [Bantu zone U, hasSubgroupingUnit, language group]
-
A.
haveSubgroups
chosen
Indicates that an entity is organized into smaller constituent groups that are part of it.
-
B.
hasSubfieldGroup
Indicates that an entity includes or is associated with a specific subgroup of related subfields within its overall structure or domain.
-
C.
hasSubgroupStatus
Indicates that one group holds a specific status or classification as a subgroup within a larger group or organization.
-
D.
hasSpecialSubgroup
Indicates that an entity includes or is associated with a particular subgroup that has distinctive or exceptional properties compared to its other subgroups.
-
E.
hasSubunits
Indicates that an entity is composed of or organized into smaller constituent units that are part of its structure.
- 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_69e77e8046888190b07ffa58c7e2c37a |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f6a8df16a88190a23820e64a3b1f92 |
completed | May 3, 2026, 1:46 a.m. |
| PD | Predicate disambiguation | batch_69f6a751d5e48190a77dcecbe7ef9f0b |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 21, 2026, 8:13 p.m.