Triple
T6701071
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Proto-Bantu |
E152878
|
entity |
| Predicate | hasCoreVocabulary |
P18536
|
FINISHED |
| Object | basic kinship terms |
—
|
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: basic kinship terms | Statement: [Proto-Bantu, hasCoreVocabulary, basic kinship terms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCoreVocabulary Context triple: [Proto-Bantu, hasCoreVocabulary, basic kinship terms]
-
A.
hasKnownVocabulary
chosen
Indicates that an entity possesses a defined, identifiable set of terms or words that it can recognize or use.
-
B.
hasVocabularyFrom
Indicates that one entity’s vocabulary, terminology, or set of terms is derived from, based on, or taken from another entity.
-
C.
hasDistinctVocabulary
Indicates that one entity’s vocabulary is different or distinguishable from that of another entity.
-
D.
hasCore
Indicates that one entity possesses, contains, or is built around a central or most essential component represented by another entity.
-
E.
hasCoreValue
Indicates that an entity possesses or is characterized by a fundamental guiding principle or core belief.
- 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_69c68807adbc8190b8632df42b39eda0 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d16897e48190b43eda2206b14d6a |
completed | March 27, 2026, 6:50 p.m. |
| PD | Predicate disambiguation | batch_69c6d089c7488190a00853fb12f53b2a |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:05 p.m.