Triple
T32232919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Francis, Duke of Anjou |
E823388
|
entity |
| Predicate | potentialSpouse |
P114351
|
FINISHED |
| Object | Elizabeth I of England |
—
|
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: Elizabeth I of England | Statement: [Francis, Duke of Anjou, potentialSpouse, Elizabeth I of England]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: potentialSpouse Context triple: [Francis, Duke of Anjou, potentialSpouse, Elizabeth I of England]
-
A.
possiblySpouse
chosen
Indicates that two entities may be spouses, reflecting an uncertain or hypothesized marital relationship between them.
-
B.
intendedSpouse
Indicates that one person is planned or expected to become the spouse of another, typically through an intended or future marriage.
-
C.
metSpouseThrough
Indicates that one person became acquainted with and subsequently married their spouse as a result of a particular intermediary person, event, place, or context.
-
D.
coSpouse
Indicates that two individuals are married to each other as spouses.
-
E.
spouseOfType
Indicates that one entity is the spouse of another, specifying the type or role of that spousal relationship.
- 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_69f3490c140481908ed53b98b561eaa1 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6bbfcb370819088ba309249ce82f1 |
completed | May 3, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69f6b632cf788190a3d0c08cd026b84b |
completed | May 3, 2026, 2:42 a.m. |
Created at: May 1, 2026, 12:39 a.m.