Triple
T33963565
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SS Empress of Scotland (1920) |
E870787
|
entity |
| Predicate | takenOutOfServiceYear |
P14100
|
FINISHED |
| Object | 1950s |
—
|
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: 1950s | Statement: [SS Empress of Scotland (1920), takenOutOfServiceYear, 1950s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: takenOutOfServiceYear Context triple: [SS Empress of Scotland (1920), takenOutOfServiceYear, 1950s]
-
A.
lastModelYearInService
Indicates the final model year during which the entity remained in active use or service.
-
B.
decommissionedDate
chosen
Indicates the date on which an entity was formally taken out of service or retired from active use.
-
C.
destructionYear
Indicates the year in which an entity was destroyed or ceased to exist due to destructive events or actions.
-
D.
lastOfClassDecommissionedYear
Indicates the year in which the final remaining member of a particular class was officially decommissioned.
-
E.
lastAppearanceYear
Indicates the calendar year in which an entity made its most recent appearance.
- 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_69f3499ce8e88190b66e1d49ad8c7037 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7064e906881909c3186c646145d34 |
completed | May 3, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69f70100ec1c8190a6b97f50e88891f2 |
completed | May 3, 2026, 8:02 a.m. |
Created at: May 1, 2026, 1:50 a.m.