Triple
T27399949
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princess of Schleswig-Holstein-Sonderburg-Augustenburg |
E691804
|
entity |
| Predicate | titleHolderMarriageYear |
P131272
|
FINISHED |
| Object | 1881 |
—
|
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: 1881 | Statement: [Princess of Schleswig-Holstein-Sonderburg-Augustenburg, titleHolderMarriageYear, 1881]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: titleHolderMarriageYear Context triple: [Princess of Schleswig-Holstein-Sonderburg-Augustenburg, titleHolderMarriageYear, 1881]
-
A.
marriageOfHeadEndYear
Indicates the year in which the head of a marriage (e.g., household or family unit) ceased to be married, marking the end of that marital relationship.
-
B.
marriedInYear
Indicates that two entities are married to each other in a specific calendar year.
-
C.
titleHoldersMarriedInto
chosen
Indicates that the holders of a particular title became related to another party through marriage.
-
D.
marriageStartTime
Indicates the date and time at which a marriage between two entities officially begins.
-
E.
titleHolderBirthDate
Indicates the date on which the person holding a particular title or position was born.
- 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_69ef5204f7048190bf226a129858fc5b |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69f7b2f3a104819098ddd8909eaf596c |
completed | May 3, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69f7b1b8a9fc8190a1279e67a2d12707 |
completed | May 3, 2026, 8:36 p.m. |
Created at: April 27, 2026, 12:29 p.m.