Triple
T37533526
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nicholas Alexandrovich, Tsarevich of Russia |
E933127
|
entity |
| Predicate | fiancéeLaterTitle |
P123942
|
FINISHED |
| Object | Empress Maria Feodorovna of Russia |
—
|
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 Maria Feodorovna of Russia | Statement: [Nicholas Alexandrovich, Tsarevich of Russia, fiancéeLaterTitle, Empress Maria Feodorovna of Russia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fiancéeLaterTitle Context triple: [Nicholas Alexandrovich, Tsarevich of Russia, fiancéeLaterTitle, Empress Maria Feodorovna of Russia]
-
A.
fiancéeLaterMarried
chosen
Indicates that a person who was once engaged to another person later went on to marry that same individual.
-
B.
fiancéePortrayedBy
Indicates that a character’s fiancée is depicted or played by a specific actor or performer.
-
C.
isFianceeOf
Indicates that one person is the engaged-to-be-married partner of another person.
-
D.
formerFiancéeOf
Indicates that one person was previously engaged to be married to another person, but the engagement has since ended.
-
E.
fiancéeDied
Indicates that a person’s fiancée has died.
- 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_69f76ec999288190ae26ec7b6aea7046 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fba5eec0448190a5e6f0c43fdcd0e3 |
completed | May 6, 2026, 8:34 p.m. |
| PD | Predicate disambiguation | batch_69fba34edd548190bfa980e6e16e0a88 |
completed | May 6, 2026, 8:23 p.m. |
Created at: May 3, 2026, 4:17 p.m.