Triple
T36762516
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SS Empress of Canada (2037) |
E908242
|
entity |
| Predicate | sharesNameSeriesWith |
P15168
|
FINISHED |
| Object | Empress of Canada (1920) |
—
|
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: Empress of Canada (1920) | Statement: [SS Empress of Canada (2037), sharesNameSeriesWith, Empress of Canada (1920)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesNameSeriesWith Context triple: [SS Empress of Canada (2037), sharesNameSeriesWith, Empress of Canada (1920)]
-
A.
sharesSeriesWith
Indicates that two entities are part of, or associated with, the same series.
-
B.
sharesNameWith
chosen
Indicates that two entities have the same name or an identical naming designation.
-
C.
sharesNameTypeWith
Indicates that two entities have the same type or category of name (e.g., both are first names, both are surnames, or both are of the same naming convention).
-
D.
sharesNameRootWith
Indicates that two entities have names derived from the same linguistic root or base form.
-
E.
sharesNameBy
Indicates that two entities have the same name or label in common.
- 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_69f76e786ba481909cdcf6cf6b39dd32 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a00a094c44c81908e4501151688a635 |
completed | May 10, 2026, 3:13 p.m. |
| PD | Predicate disambiguation | batch_6a009fcdfd848190841deaad9667d347 |
completed | May 10, 2026, 3:10 p.m. |
Created at: May 3, 2026, 4:12 p.m.