Triple
T34272356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SS Empress of Canada (1957) |
E879352
|
entity |
| Predicate | operatorAfterSale |
P166190
|
FINISHED |
| Object | Carnival Cruise Lines |
—
|
NE NERFINISHED |
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: Carnival Cruise Lines | Statement: [SS Empress of Canada (1957), operatorAfterSale, Carnival Cruise Lines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatorAfterSale Context triple: [SS Empress of Canada (1957), operatorAfterSale, Carnival Cruise Lines]
-
A.
soldAfter
Indicates that one item was sold at a later time than another item.
-
B.
laterSells
Indicates that one entity sells or transfers ownership of something to another entity at a later point in time relative to some reference event or time.
-
C.
describesCreativeReturnAfter
Indicates that an entity produces or provides a creative work, response, or output following a prior action, request, or event.
-
D.
afterService
Indicates that one event, action, or state occurs subsequent to the completion of a specified service.
-
E.
ownershipAfterPurchase
chosen
Indicates that an entity comes to own another entity as a result of completing a purchase transaction.
- 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_69f349b4f5fc819094b441d18e95e5f1 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a00ae638fcc819096537b2c21366161 |
completed | May 10, 2026, 4:12 p.m. |
| PD | Predicate disambiguation | batch_6a00ae0551988190bcb3564ed9af2847 |
completed | May 10, 2026, 4:10 p.m. |
Created at: May 1, 2026, 1:56 a.m.