Triple
T6701033
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Proto-Bantu |
E152878
|
entity |
| Predicate | reconstructedByMethod |
P30323
|
FINISHED |
| Object | comparative method |
—
|
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: comparative method | Statement: [Proto-Bantu, reconstructedByMethod, comparative method]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reconstructedByMethod Context triple: [Proto-Bantu, reconstructedByMethod, comparative method]
-
A.
reconstructionMethod
chosen
Indicates the technique or process used to reconstruct, restore, or rebuild something from its original or fragmented state.
-
B.
reconstructedAs
Indicates that one entity has been rebuilt, recreated, or inferred based on evidence, models, or partial information from another entity.
-
C.
reconstructedAfter
Indicates that one entity has been rebuilt, restored, or reassembled following the occurrence or existence of another entity or event.
-
D.
reconstructedIn
Indicates that something has been rebuilt, restored, or re-created within a particular context, location, or medium.
-
E.
containsReconstructionOf
Indicates that one entity includes or incorporates a recreated, restored, or reconstructed version of 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_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.