Triple
T21311034
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sophia Alekseyevna Romanova |
E525333
|
entity |
| Predicate | afterDownfallStatus |
P49654
|
FINISHED |
| Object | nun at Novodevichy Convent |
—
|
LITERAL 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: nun at Novodevichy Convent | Statement: [Sophia Alekseyevna Romanova, afterDownfallStatus, nun at Novodevichy Convent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: afterDownfallStatus Context triple: [Sophia Alekseyevna Romanova, afterDownfallStatus, nun at Novodevichy Convent]
-
A.
fallStatus
Indicates the condition or outcome of a fall event affecting an entity.
-
B.
downfall
Indicates the process or event by which an entity experiences a significant decline, ruin, or loss of power, status, or success.
-
C.
demiseOfStatus
chosen
Indicates the ending or loss of a previously held status, role, or condition for an entity.
-
D.
statusAfterBattle
Indicates the condition or state of an entity following the completion of a battle or combat encounter.
-
E.
afterDeath
Indicates that one event, state, or condition occurs subsequent to and as a result of an entity’s death.
- 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_69e0b518b8948190ad69cf9a8784d397 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e75dc926c881909d70a317070ef295 |
completed | April 21, 2026, 11:21 a.m. |
| PD | Predicate disambiguation | batch_69e61612ab748190a72b8703b938abcb |
completed | April 20, 2026, 12:03 p.m. |
Created at: April 16, 2026, 4:13 p.m.