Triple
T723813
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UC Berkeley wordmarks |
E14675
|
entity |
| Predicate | fileType |
P8462
|
FINISHED |
| Object | vector files |
—
|
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: vector files | Statement: [UC Berkeley wordmarks, fileType, vector files]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fileType Context triple: [UC Berkeley wordmarks, fileType, vector files]
-
A.
mediaType
Indicates the format or category of media associated with an entity, such as text, image, audio, or video.
-
B.
hasFileFormat
chosen
Indicates that one entity (typically a digital file or resource) is encoded, stored, or represented using a specific file format defined by the other entity.
-
C.
dataTransferType
Indicates the method or mode by which data is transmitted or exchanged between entities.
-
D.
frameType
Indicates the specific structural or categorical kind of frame associated with an entity or relation.
-
E.
fieldType
Indicates the classification or category that defines the nature or kind of a given field within a structure or 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_69a4934c753c81909b309027e48b9b3a |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a5a5360c8190b16e1e4f4206d0aa |
completed | March 1, 2026, 8:46 p.m. |
| PD | Predicate disambiguation | batch_69a4a4f700cc81908c6de3eedf68433c |
completed | March 1, 2026, 8:43 p.m. |
Created at: March 1, 2026, 7:37 p.m.