Triple
T18859548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Augusta Victoria of Hohenzollern |
E461271
|
entity |
| Predicate | hadNoChildrenWith |
P38071
|
FINISHED |
| Object | Manuel II of Portugal |
—
|
NE NERFINISHED |
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: Manuel II of Portugal | Statement: [Augusta Victoria of Hohenzollern, hadNoChildrenWith, Manuel II of Portugal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadNoChildrenWith Context triple: [Augusta Victoria of Hohenzollern, hadNoChildrenWith, Manuel II of Portugal]
-
A.
hadChildren
Indicates that the subject person is a parent of one or more children.
-
B.
hadNoSurvivingChildren
Indicates that the person did not have any children who were alive at the relevant point in time.
-
C.
hadChildrenOrganization
Indicates that an organization created, founded, or was otherwise responsible for bringing into existence one or more subordinate or successor organizations.
-
D.
hadNo
chosen
Indicates that one entity completely lacked or did not possess another entity, attribute, or relationship.
-
E.
hadSibling
Indicates that one entity and another entity share at least one parent, i.e., they are siblings.
- 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_69d8dcfb7b9c8190854e7b171b98ea2e |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c05fb800819098951ec134a1fa2a |
completed | April 20, 2026, 5:57 a.m. |
| PD | Predicate disambiguation | batch_69e48d2166b88190add38de96cedc65c |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:57 a.m.