Triple
T22364023
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Register of Archives |
E552853
|
entity |
| Predicate | maintainsInformationOn |
P37873
|
FINISHED |
| Object | historical 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: historical records | Statement: [National Register of Archives, maintainsInformationOn, historical records]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maintainsInformationOn Context triple: [National Register of Archives, maintainsInformationOn, historical records]
-
A.
collectsInformationOn
Indicates that one entity gathers or acquires data, facts, or details about another entity.
-
B.
maintainsThrough
Indicates that one entity preserves, upholds, or continues a state, condition, or relationship by means of another specified entity, process, or medium.
-
C.
dataMaintained
chosen
Indicates that one entity is responsible for preserving, storing, or keeping another entity’s data up to date and accessible over time.
-
D.
maintainedFor
Indicates that something is kept in a particular state, condition, or operation for the benefit, use, or purpose of another entity.
-
E.
providesInformationIn
Indicates that one entity supplies or conveys information within or through another entity or context.
- 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_69e11e4affcc8190ba7c27d29062558d |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f157d616748190921bd49039b7f6fc |
completed | April 29, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69e73011e6388190a05edf137f488441 |
completed | April 21, 2026, 8:06 a.m. |
Created at: April 16, 2026, 8:44 p.m.