Triple
T26985676
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kiln People |
E679729
|
entity |
| Predicate | copyProperty |
P128034
|
FINISHED |
| Object | can download memories back to original |
—
|
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: can download memories back to original | Statement: [Kiln People, copyProperty, can download memories back to original]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: copyProperty Context triple: [Kiln People, copyProperty, can download memories back to original]
-
A.
copyType
Indicates that one entity is a copy or duplication of another, specifying the type or manner of that copying relationship.
-
B.
targetProperty
Indicates that one entity serves as the intended goal, focus, or object of another entity’s action, influence, or effect.
-
C.
changesProperty
Indicates that one entity causes a change in a specific property or attribute of another entity.
-
D.
copySemantics
chosen
Indicates how the behavior or state of one entity is duplicated, shared, or independently copied in relation to another entity.
-
E.
transformationProperty
Indicates that one entity has a specific behavior, constraint, or characteristic related to how it changes, converts, or is transformed into another form or state.
- 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_69eeeb5138ac8190b3c273ddc659a54f |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f6215954f8819092cf882ca976fafa |
completed | May 2, 2026, 4:07 p.m. |
| PD | Predicate disambiguation | batch_69f611af72ac819094598dd2530d7411 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 6:48 a.m.