Triple
T1300882
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prince Harry, Duke of Sussex |
E27759
|
entity |
| Predicate | announcedStepBackFromRoyalDuties |
P26777
|
FINISHED |
| Object | 2020 |
—
|
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: 2020 | Statement: [Prince Harry, Duke of Sussex, announcedStepBackFromRoyalDuties, 2020]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: announcedStepBackFromRoyalDuties Context triple: [Prince Harry, Duke of Sussex, announcedStepBackFromRoyalDuties, 2020]
-
A.
reasonForAbdication
Indicates the specific cause, motive, or circumstances that led an individual to formally abdicate a position of authority or power.
-
B.
reignAsPrincessConsortEnd
Indicates the time or event at which an individual’s tenure as princess consort comes to an end.
-
C.
abdicatedFrom
Indicates that a person has formally renounced or given up a position of authority, office, or throne associated with a particular entity or domain.
-
D.
abdicatedInFavorOf
Indicates that one entity has voluntarily renounced a position, role, or right so that another specific entity may assume it.
-
E.
dateOfAbdication
Indicates the specific date on which a person formally relinquishes a position of authority or throne.
- F. None of above. chosen
Provenance (4 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_69a496d6682881909ba658f1c1e0e2b0 |
completed | March 1, 2026, 7:43 p.m. |
| NER | Named-entity recognition | batch_69a4c1145c2481908adf22dfd6ce349b |
completed | March 1, 2026, 10:43 p.m. |
| PD | Predicate disambiguation | batch_69a4bee8544c8190874efd9bae9bccf9 |
completed | March 1, 2026, 10:34 p.m. |
| PDg | Predicate description generation | batch_69a4bf60545c8190901ccfb2cb7c4b41 |
completed | March 1, 2026, 10:36 p.m. |
Created at: March 1, 2026, 7:51 p.m.