Triple
T31878323
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dowager Duchess |
E813804
|
entity |
| Predicate | titlePersistsAfter |
P13879
|
FINISHED |
| Object | death of the duke |
—
|
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: death of the duke | Statement: [Dowager Duchess, titlePersistsAfter, death of the duke]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titlePersistsAfter Context triple: [Dowager Duchess, titlePersistsAfter, death of the duke]
-
A.
titleRetainedAfter
chosen
Indicates that an entity continues to hold or use the same title after a specified event or point in time.
-
B.
titleAfterCase
Indicates that a title or designation is assigned to or used for an entity only after a particular case, event, or legal proceeding has occurred.
-
C.
titleThrough
Indicates a relationship where one entity holds or is identified by a specific title by means of, or via the mediation of, another entity or context.
-
D.
titleBecomes
Indicates that one title changes into or is replaced by another title over time.
-
E.
titleContinuesAs
Indicates that one title is succeeded or carried on by another title as its continuation.
- 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_69f348ed74bc81909846aaa6a3c7318c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fe8ddf70e48190a917eb9e8f7b6966 |
completed | May 9, 2026, 1:29 a.m. |
| PD | Predicate disambiguation | batch_69fe87ef94dc81909bb00ec8d6de9bcd |
completed | May 9, 2026, 1:03 a.m. |
Created at: April 30, 2026, 11:55 p.m.