Triple
T29636178
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | VQ-VAE |
E755720
|
entity |
| Predicate | latentRepresentation |
P10727
|
FINISHED |
| Object | indices into a codebook of 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: indices into a codebook of embeddings | Statement: [VQ-VAE, latentRepresentation, indices into a codebook of embeddings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: latentRepresentation Context triple: [VQ-VAE, latentRepresentation, indices into a codebook of embeddings]
-
A.
spatialRepresentation
Indicates that one entity serves as a spatial depiction, model, or encoding of the location, layout, or geometric properties of another entity.
-
B.
reducedRepresentationOf
chosen
Indicates that one entity is a simplified, compressed, or lower-detail version of another entity while preserving its essential information or structure.
-
C.
stateRepresentation
Indicates that one entity serves as a depiction, model, or encoding of the condition, configuration, or status of another entity.
-
D.
featuresRepresentationOf
Indicates that one entity visually or symbolically depicts, portrays, or includes a representation of another entity.
-
E.
representationIn
Indicates that one entity serves as a depiction, model, or stand-in for another entity within a given context or medium.
- 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_69f0ef88fbe081908f0ad90c1c413f1c |
completed | April 28, 2026, 5:34 p.m. |
| NER | Named-entity recognition | batch_69f66e6a2790819082fb230e553bf4c5 |
completed | May 2, 2026, 9:36 p.m. |
| PD | Predicate disambiguation | batch_69f6659d36208190b01412600a4ed57d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 6:44 p.m.