Triple
T34580658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SS Empress of Canada (1966) |
E887888
|
entity |
| Predicate | enteredCarnivalServiceAs |
P180833
|
FINISHED |
| Object | Mardi Gras |
—
|
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: Mardi Gras | Statement: [SS Empress of Canada (1966), enteredCarnivalServiceAs, Mardi Gras]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: enteredCarnivalServiceAs Context triple: [SS Empress of Canada (1966), enteredCarnivalServiceAs, Mardi Gras]
-
A.
enteredServiceOn
Indicates the date or time when an entity first began active use, operation, or service.
-
B.
enteredService
Indicates that an entity began active use or operation at a specific time or in a specific context.
-
C.
enterAs
chosen
Indicates that one entity goes into or joins another context, place, or role in the capacity or form specified.
-
D.
enteredServiceInCity
Indicates that an entity began its operational service or official use within a specified city.
-
E.
enteredServiceRole
Indicates that an entity has begun serving in a particular role, position, or capacity.
- 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_69f349d25cbc8190869998de5915886b |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f7886be6d8819095ec62e4f2cee858 |
completed | May 3, 2026, 5:39 p.m. |
| PD | Predicate disambiguation | batch_69f7841440f48190b4346c08855951d2 |
completed | May 3, 2026, 5:21 p.m. |
Created at: May 1, 2026, 2:03 a.m.