Triple
T17690408
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FKT |
E441008
|
entity |
| Predicate | changeToCurrentOffsetYear |
P84678
|
FINISHED |
| Object | 2010s (approximate) |
—
|
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: 2010s (approximate) | Statement: [FKT, changeToCurrentOffsetYear, 2010s (approximate)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: changeToCurrentOffsetYear Context triple: [FKT, changeToCurrentOffsetYear, 2010s (approximate)]
-
A.
movedToCurrentDateYear
Indicates that an entity has been moved, updated, or adjusted so that its associated date now falls within the current calendar year.
-
B.
movedToCurrentDateBy
Indicates that something has been rescheduled, adjusted, or shifted so that it now occurs or is set on the current date by a particular agent or process.
-
C.
calendarYearOffsetFromGregorian
chosen
Indicates the number of whole calendar years by which a given calendar system is offset relative to the Gregorian calendar.
-
D.
movedToInYear
Indicates that an entity changed location or residence to a specified place in a particular year.
-
E.
pastSettingYear
Indicates that an event, narrative, or situation is set in or associated with a specific year in the past.
- 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_69d8b9e940b081908b862bb0e6e89b0d |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4704b43a88190ba29654ca695839e |
completed | April 19, 2026, 6:03 a.m. |
| PD | Predicate disambiguation | batch_69e3cde3673c8190a889e14ba1f07dc1 |
completed | April 18, 2026, 6:30 p.m. |
Created at: April 10, 2026, 10:03 a.m.