Triple
T18724389
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BERT |
E457858
|
entity |
| Predicate | inputEmbedding |
P7030
|
FINISHED |
| Object | sum of token, segment, and position embeddings |
—
|
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: sum of token, segment, and position embeddings | Statement: [BERT, inputEmbedding, sum of token, segment, and position embeddings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inputEmbedding Context triple: [BERT, inputEmbedding, sum of token, segment, and position embeddings]
-
A.
embeddingType
chosen
Indicates the specific kind or category of embedding representation used to encode an entity or data.
-
B.
input
Indicates that one entity provides data, signals, or resources that are received or processed by another entity.
-
C.
encodedIn
Indicates that one entity is represented, stored, or expressed within another entity using a specific encoding or format.
-
D.
inputType
Indicates the kind or format of data that an entity expects to receive as input in a given context.
-
E.
inputIs
Indicates that one entity serves as the input or provided value to another entity, process, or function.
- 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_69d8d393ba9c8190a8b03b04ddbb0a09 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e56abcfc048190a01dee959e768768 |
completed | April 19, 2026, 11:52 p.m. |
| PD | Predicate disambiguation | batch_69e48d03766c8190a43f7681842f4f8d |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:50 a.m.