Triple
T671810
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Film Registry |
E12986
|
entity |
| Predicate | selectionAnnouncementFrequency |
P85
|
FINISHED |
| Object | once per year |
—
|
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: once per year | Statement: [National Film Registry, selectionAnnouncementFrequency, once per year]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: selectionAnnouncementFrequency Context triple: [National Film Registry, selectionAnnouncementFrequency, once per year]
-
A.
awardedFrequency
Indicates how often an award or recognition is given within a specified time period.
-
B.
selectionRankingFrequency
Indicates how often an entity is chosen or ranked in a particular position within a selection or ordering process.
-
C.
typicalAnnouncementTime
Indicates the usual or standard time at which an announcement is made or expected to occur.
-
D.
frequency
chosen
Indicates how often an event, action, or relationship occurs within a given period or context.
-
E.
frequencyDependsOn
Indicates that the frequency of one event, action, or state is determined or influenced by another factor or condition.
- 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_69a493355dec819098d4244b2fa34885 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4a1b3682c8190a9b9a454480c3446 |
completed | March 1, 2026, 8:29 p.m. |
| PD | Predicate disambiguation | batch_69a49d1a16c48190af89e3b078a4957e |
completed | March 1, 2026, 8:10 p.m. |
Created at: March 1, 2026, 7:36 p.m.