Triple
T4651133
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Transformer |
E102296
|
entity |
| Predicate | inputRepresentation |
P11909
|
FINISHED |
| Object | token 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: token embeddings | Statement: [Transformer, inputRepresentation, token embeddings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inputRepresentation Context triple: [Transformer, inputRepresentation, token embeddings]
-
A.
representationType
Indicates the specific form or mode in which something is represented or expressed (e.g., as a symbol, image, model, or description).
-
B.
formerRepresentation
Indicates that one entity previously served as the representative (e.g., legal, political, or organizational) of another entity, but no longer holds that role.
-
C.
inputType
chosen
Indicates the kind or format of data that an entity expects to receive as input in a given context.
-
D.
componentRepresents
Indicates that one component stands in for, symbolizes, or models another entity or concept within a system or context.
-
E.
representation
Indicates that one entity stands in for, symbolizes, or depicts another entity in some context.
- 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_69bd43d71a308190afea7280841b0de8 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd6632708c8190b627d99363ab062c |
completed | March 20, 2026, 3:22 p.m. |
| PD | Predicate disambiguation | batch_69bd620fc5e081908325ac8e6a6384ab |
completed | March 20, 2026, 3:04 p.m. |
Created at: March 20, 2026, 1:14 p.m.