Triple
T10117601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Defense Authorization Act for Fiscal Year 1997 |
E223201
|
entity |
| Predicate | frequencyOfRequiredReview |
P8512
|
FINISHED |
| Object | every four years |
—
|
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: every four years | Statement: [National Defense Authorization Act for Fiscal Year 1997, frequencyOfRequiredReview, every four years]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frequencyOfRequiredReview Context triple: [National Defense Authorization Act for Fiscal Year 1997, frequencyOfRequiredReview, every four years]
-
A.
areReviewedEvery
Indicates that one entity conducts reviews of another entity at every specified time interval or on every relevant occasion.
-
B.
frequencyRequirement
chosen
Indicates a constraint specifying how often an action, event, or condition must occur within a given context or time frame.
-
C.
appointmentFrequency
Indicates how often appointments are scheduled or expected to occur within a given time period.
-
D.
hasReviewPeriod
Indicates that an entity is associated with a specific time span during which it is subject to review or evaluation.
-
E.
performedFrequency
Indicates how often an action or activity is carried out within a given time period.
- 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_69ca8422047c81909d66b717b8b18cf3 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cdd26317948190901197adbac01ed3 |
completed | April 2, 2026, 2:20 a.m. |
| PD | Predicate disambiguation | batch_69cd4b9ed7e48190aa132ef8a69b49f9 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:04 p.m.