Triple
T24967728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bantu zone F |
E624794
|
entity |
| Predicate | hasDefiner |
P152925
|
FINISHED |
| Object | Malcolm Guthrie |
—
|
NE NERFINISHED |
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: Malcolm Guthrie | Statement: [Bantu zone F, hasDefiner, Malcolm Guthrie]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDefiner Context triple: [Bantu zone F, hasDefiner, Malcolm Guthrie]
-
A.
hasDefinition
Indicates that one entity provides the meaning, explanation, or definition of another entity.
-
B.
wasDefinedBy
chosen
Indicates that something was formally specified, described, or established by a particular agent, source, or defining entity.
-
C.
areDefinedIn
Indicates that the referenced entities are specified, described, or formally established within a particular source, context, or scope.
-
D.
canBeDefinedFor
Indicates that a certain concept, operation, or property is applicable to and can be meaningfully specified for a given entity or set of entities.
-
E.
endDefinedBy
Indicates that the termination or boundary of one entity is determined, specified, or constrained by 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_69e2ff24512481908e9a72315b8d0354 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f621fcea1481909b6f8b3af1ee6820 |
completed | May 2, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69f620dc38088190b56b2b15ed75b3c2 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 18, 2026, 6 a.m.