Triple
T960739
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princess Elisabeth, Duchess of Brabant |
E20729
|
entity |
| Predicate | heirStatusStartDate |
P6561
|
FINISHED |
| Object | 2013-07-21 |
—
|
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: 2013-07-21 | Statement: [Princess Elisabeth, Duchess of Brabant, heirStatusStartDate, 2013-07-21]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heirStatusStartDate Context triple: [Princess Elisabeth, Duchess of Brabant, heirStatusStartDate, 2013-07-21]
-
A.
ordinationDate
Indicates the date on which an individual was formally ordained to a religious office or role.
-
B.
dateGranted
chosen
Indicates the specific date on which a right, status, or permission was formally conferred or approved.
-
C.
establishedFrom
Indicates that something was created, founded, or formed starting from a specified source, origin, or prior entity.
-
D.
previousHolderStartDate
Indicates the date on which the immediately preceding holder of something (e.g., a position, title, or asset) began their tenure or ownership.
-
E.
designationDate
Indicates the date on which an entity is formally assigned, designated, or given a particular status or role.
- 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_69a493b21f2881908132dcf45dcd2f36 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b4144c208190980936347a95e233 |
completed | March 1, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69a4b2a2e23c8190b932fe88b02f995d |
completed | March 1, 2026, 9:41 p.m. |
Created at: March 1, 2026, 7:40 p.m.