Triple
T1218493
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prince Albert Victor, Duke of Clarence and Avondale |
E26162
|
entity |
| Predicate | dateOfCreationOfTitle |
P3359
|
FINISHED |
| Object | 1890-05-24 |
—
|
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: 1890-05-24 | Statement: [Prince Albert Victor, Duke of Clarence and Avondale, dateOfCreationOfTitle, 1890-05-24]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dateOfCreationOfTitle Context triple: [Prince Albert Victor, Duke of Clarence and Avondale, dateOfCreationOfTitle, 1890-05-24]
-
A.
dateOfComposition
Indicates the calendar date or time period when a particular work was created or composed.
-
B.
createdAt
Indicates the date and time at which an entity was initially created or came into existence.
-
C.
createdAtRidge
Indicates that something was created or originated at a specific ridge location.
-
D.
cardinalCreationDate
chosen
Indicates the specific date on which something was originally created or brought into existence.
-
E.
createdAs
Indicates that one entity was originally made, designed, or brought into existence in the form, role, or identity specified by another entity.
- 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_69a4948331fc8190b531ac9bec71c491 |
completed | March 1, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69a4be08157c8190b248bb75b922644f |
completed | March 1, 2026, 10:30 p.m. |
| PD | Predicate disambiguation | batch_69a4bb62a7c08190a79dcb6ff72ac99b |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:46 p.m.