Triple
T14573890
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prince Charles of Belgium |
E341987
|
entity |
| Predicate | startTime (as Prince Regent of Belgium) |
P114919
|
FINISHED |
| Object | 1944-09-20 |
—
|
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: 1944-09-20 | Statement: [Prince Charles of Belgium, startTime (as Prince Regent of Belgium), 1944-09-20]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startTime (as Prince Regent of Belgium) Context triple: [Prince Charles of Belgium, startTime (as Prince Regent of Belgium), 1944-09-20]
-
A.
startTime (Duke of Bavaria)
Indicates the point in time at which the person began holding the title or office of Duke of Bavaria.
-
B.
reignAsCrownPrinceFrom
Indicates the period during which a person holds and exercises the official status and role of crown prince of a particular realm or title.
-
C.
reignAsKingOfBurgundyStart
Indicates the time at which an individual begins their reign as king over the realm of Burgundy.
-
D.
reignAsDukeOfNassauStart
Indicates the time at which an individual begins their tenure ruling in the position of Duke of Nassau.
-
E.
reignAsPrinceEnd
Indicates the point in time or event at which an individual’s tenure or role as a prince comes to an end.
- 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_69d822dcc6248190bed689984bceb0e2 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb3f49d58819094fcd2a702e146cb |
completed | April 14, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69de656a953481909a4645b004c40de7 |
completed | April 14, 2026, 4:03 p.m. |
| PDg | Predicate description generation | batch_69de716c17cc8190aeb85296abee85a7 |
completed | April 14, 2026, 4:55 p.m. |
Created at: April 10, 2026, 1:24 a.m.