Triple
T4769030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atbash |
E105879
|
entity |
| Predicate | preservesSpacing |
P36966
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Atbash, preservesSpacing, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: preservesSpacing Context triple: [Atbash, preservesSpacing, true]
-
A.
preservesFeature
Indicates that one entity maintains or keeps intact a particular feature, property, or characteristic of another entity during some process or interaction.
-
B.
preservesFragmentsOf
Indicates that one entity maintains, protects, or keeps intact partial remains or pieces of another entity.
-
C.
preservesLanguage
Indicates that an entity actively maintains, protects, or continues the use of a particular language so it does not decline or disappear.
-
D.
isWrittenWithSpace
chosen
Indicates that something is written or represented with spaces separating its components or elements.
-
E.
parityMaintainedWith
Indicates that a state of equality or balance (such as value, status, or conditions) is preserved between two entities over time.
- 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_69bd43f226fc8190b867cc249c2a9042 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd655aceb081908100ffc0498fe183 |
completed | March 20, 2026, 3:18 p.m. |
| PD | Predicate disambiguation | batch_69bd6229d8448190a271719e5e30fd82 |
completed | March 20, 2026, 3:05 p.m. |
Created at: March 20, 2026, 1:21 p.m.