Triple
T305465
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Presidential Records Act |
E6287
|
entity |
| Predicate | distinguishesBetween |
P3450
|
FINISHED |
| Object | presidential records and personal records |
—
|
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: presidential records and personal records | Statement: [Presidential Records Act, distinguishesBetween, presidential records and personal records]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distinguishesBetween Context triple: [Presidential Records Act, distinguishesBetween, presidential records and personal records]
-
A.
distinction
chosen
Indicates that one entity is recognized, treated, or classified as different or separate from another.
-
B.
uniformDistinction
Indicates that a clear and consistent difference is maintained between two or more entities within a given context.
-
C.
distinguishingNotation
Indicates that one entity uses a specific notation or symbol to distinguish or differentiate another entity from similar ones.
-
D.
separates
Indicates that one entity divides, parts, or keeps other entities apart from each other.
-
E.
dividedBetween
Indicates that something is partitioned or shared among two or more distinct entities or groups.
- 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_69a2e79230508190b912ecb555aae17e |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2ea11c4908190a8723033bdf6f479 |
completed | Feb. 28, 2026, 1:13 p.m. |
| PD | Predicate disambiguation | batch_69a2e93db11881909b07ba5e76d91feb |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:06 p.m.