Triple
T34165716
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Order of Saint Catherine |
E876404
|
entity |
| Predicate | firstGrandMistress |
P205349
|
FINISHED |
| Object | Catherine I of Russia |
E15120
|
NE 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: Catherine I of Russia | Statement: [Order of Saint Catherine, firstGrandMistress, Catherine I of Russia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstGrandMistress Context triple: [Order of Saint Catherine, firstGrandMistress, Catherine I of Russia]
-
A.
royalMistressOf
Indicates that one person is the (typically unofficial) romantic or sexual partner of a royal figure, such as a king or prince.
-
B.
firstGrandInquisitor
Indicates that one entity holds the role or title of the very first Grand Inquisitor in relation to a specified group, institution, or context.
-
C.
firstHolderMother
Indicates that the first holder in a given context is the mother of the related entity.
-
D.
hadMistress
Indicates that a person maintained an extramarital or unofficial romantic/sexual relationship with another person.
-
E.
firstDuchessInHerOwnRight
Indicates that a person is the first woman to hold the title of duchess in her own legal right, rather than through marriage or courtesy.
- F. None of above. chosen
Provenance (5 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_69f349ac987481908a8e6053f665bc8b |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a037c92f03c8190ae2751270b195423 |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a36c1d7070c8190bd08e16196c67256 |
completed | June 20, 2026, 4:37 p.m. |
| PD | Predicate disambiguation | batch_6a0379f963908190846d232f386fd98f |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c80ba448190853011097a151b7e |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 1, 2026, 1:54 a.m.