Triple
T36699666
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SS Empress of Canada (2036) |
E906189
|
entity |
| Predicate | hasPlannedLaunchPeriod |
P196026
|
FINISHED |
| Object | 2030s |
—
|
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: 2030s | Statement: [SS Empress of Canada (2036), hasPlannedLaunchPeriod, 2030s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPlannedLaunchPeriod Context triple: [SS Empress of Canada (2036), hasPlannedLaunchPeriod, 2030s]
-
A.
hasPlannedLaunchYear
Indicates the year in which an entity’s launch is scheduled or planned to occur.
-
B.
originalPlannedLaunchYear
Indicates the year that was initially scheduled or intended for an entity’s launch before any delays or changes.
-
C.
hasPlanningPeriod
Indicates that an entity is associated with a defined time span allocated for planning activities.
-
D.
hasLaunch
Indicates that an entity initiates or carries out the launch of another entity (such as a product, mission, or event).
-
E.
hasApproximateCommissioningPeriod
Indicates that an entity is associated with a commissioning time frame that is known only approximately rather than as a precise date.
- 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_69f76e7195c48190b5580c9cfb01e95f |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fe00dad1708190b6522476bebb43af |
completed | May 8, 2026, 3:27 p.m. |
| PD | Predicate disambiguation | batch_69fdfc3717f48190bb50ac2919c8ef95 |
completed | May 8, 2026, 3:07 p.m. |
| PDg | Predicate description generation | batch_69fe00d8d8248190a63c12aa2c2f7c0c |
completed | May 8, 2026, 3:27 p.m. |
Created at: May 3, 2026, 4:12 p.m.