Triple
T17706321
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Washington memorabilia |
E441440
|
entity |
| Predicate | preservedFor |
P128664
|
FINISHED |
| Object | historical research |
—
|
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: historical research | Statement: [George Washington memorabilia, preservedFor, historical research]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: preservedFor Context triple: [George Washington memorabilia, preservedFor, historical research]
-
A.
somePreservedAs
Indicates that at least one part or instance of an entity is kept or maintained in a particular state, form, or condition.
-
B.
isPreservedBy
Indicates that something remains unchanged, intact, or maintained as it is due to the action or influence of a particular agent or process.
-
C.
preservedAt
Indicates that something is kept, maintained, or conserved in a particular place or context.
-
D.
preservedPart
Indicates that one entity is a remaining or conserved portion of another entity that has been kept intact over time.
-
E.
preservedExample
Indicates that an example instance has been kept intact or maintained in its original state for future reference or use.
- F. None of above. chosen
Provenance (4 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_69d8b9ea20b48190ace88bb46b01e6a9 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e47297f7188190ba859d71e394bd4b |
completed | April 19, 2026, 6:13 a.m. |
| PD | Predicate disambiguation | batch_69e3cde601d4819097903f471f1fe99a |
completed | April 18, 2026, 6:31 p.m. |
| PDg | Predicate description generation | batch_69e3d018227c8190b6624a2199e765e8 |
completed | April 18, 2026, 6:40 p.m. |
Created at: April 10, 2026, 10:05 a.m.