Triple
T10848895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | multiannual financial framework of the European Union |
E256087
|
entity |
| Predicate | previousPeriod |
P96058
|
FINISHED |
| Object | 2014–2020 |
—
|
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: 2014–2020 | Statement: [multiannual financial framework of the European Union, previousPeriod, 2014–2020]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousPeriod Context triple: [multiannual financial framework of the European Union, previousPeriod, 2014–2020]
-
A.
previousSeason
Indicates that one season directly precedes another in chronological order within the same series or competition.
-
B.
previousMonthOfOccurrence
Indicates that one time period is the month immediately preceding the month in which a specified event or occurrence takes place.
-
C.
chronologyPreviousYear
Indicates that one time-related entity occurs exactly one calendar year before another in a chronological sequence.
-
D.
previousPost
Indicates that one post directly precedes another in a sequence or ordered list of posts.
-
E.
previousElectionYear
Indicates the year in which the immediately preceding election for the same office, position, or body took place.
- 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_69d6aa81a5d08190aa86689061d1ddd2 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d75114ca988190a0e730131adb2df0 |
completed | April 9, 2026, 7:11 a.m. |
| PD | Predicate disambiguation | batch_69d70d2b51448190bae748ed6c23edde |
completed | April 9, 2026, 2:21 a.m. |
| PDg | Predicate description generation | batch_69d7101c96708190808fef73199e8482 |
completed | April 9, 2026, 2:34 a.m. |
Created at: April 8, 2026, 9:20 p.m.