Triple
T32665931
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Future Years Defense Program |
E835154
|
entity |
| Predicate | timeframeUpdated |
P175020
|
FINISHED |
| Object | annually |
—
|
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: annually | Statement: [Future Years Defense Program, timeframeUpdated, annually]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timeframeUpdated Context triple: [Future Years Defense Program, timeframeUpdated, annually]
-
A.
timeframeRelative
Indicates a temporal relationship where one event, state, or condition is positioned in time relative to another (e.g., before, after, or overlapping).
-
B.
timeframeApproximate
Indicates that the time period associated with an event or relation is not exact but only roughly or loosely specified.
-
C.
timeFrameSpecified
Indicates that a specific temporal period or duration has been explicitly defined or constrained for the related event, action, or relationship.
-
D.
timeFrameTraditionallyLinked
Indicates that one time frame is customarily or historically associated with another, reflecting a traditional linkage between them.
-
E.
timeframeOfGreatestSuccess
Indicates the period during which an entity achieved its highest level of success or peak performance.
- 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_69f349303ccc8190a70d0f6e8a21d3fb |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6cd9bae8c8190b528641499162a75 |
completed | May 3, 2026, 4:22 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1470808190b70cdfd7a6395670 |
completed | May 3, 2026, 4:16 a.m. |
| PDg | Predicate description generation | batch_69f6cd119cac8190a0b3ebe8b9c742c2 |
completed | May 3, 2026, 4:20 a.m. |
Created at: May 1, 2026, 1:08 a.m.