Triple
T13091672
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Colossus computers |
E310475
|
entity |
| Predicate | processingMode |
P13489
|
FINISHED |
| Object | stream processing of cipher text from tape |
—
|
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: stream processing of cipher text from tape | Statement: [Colossus computers, processingMode, stream processing of cipher text from tape]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: processingMode Context triple: [Colossus computers, processingMode, stream processing of cipher text from tape]
-
A.
processingUse
Indicates that one entity uses or applies another entity as part of a processing or transformation activity.
-
B.
exportMode
Indicates the method or configuration by which data, content, or resources are exported from one system or context to another.
-
C.
processingOrder
Indicates the sequence or priority in which items, tasks, or requests are to be processed or handled.
-
D.
processType
chosen
Indicates the specific kind or category of process that an entity or activity belongs to.
-
E.
intendedPerformanceMode
Indicates the manner or mode in which an action, process, or performance is meant or designed to be carried out.
- 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_69d806a733548190989cfd4ce981ca33 |
completed | April 9, 2026, 8:05 p.m. |
| NER | Named-entity recognition | batch_69d9813acbac8190b2fe5e07287457cf |
completed | April 10, 2026, 11:01 p.m. |
| PD | Predicate disambiguation | batch_69d9803f6c508190bfadfbc2d00c2c64 |
completed | April 10, 2026, 10:57 p.m. |
Created at: April 9, 2026, 9:03 p.m.