Triple
T36460452
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Philibert II, Duke of Savoy |
E898273
|
entity |
| Predicate | secondSpouse |
P14424
|
FINISHED |
| Object | Margaret of Austria |
—
|
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: Margaret of Austria | Statement: [Philibert II, Duke of Savoy, secondSpouse, Margaret of Austria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondSpouse Context triple: [Philibert II, Duke of Savoy, secondSpouse, Margaret of Austria]
-
A.
secondWifeOf
chosen
Indicates that one person is the second spouse (by order of marriage) of another person.
-
B.
secondHolderSpouse
Indicates that the second holder in a given context is married to the referenced spouse.
-
C.
subsequentSpouse
Indicates that one person is a later spouse of another, following a previous marriage involving at least one of them.
-
D.
secondHusbandInstanceOf
Indicates that one person is the second husband of another person in a sequence of marital relationships.
-
E.
exSpouse
Indicates that two people were formerly married to each other but are no longer spouses.
- 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_69f76e57f08481908593bd0bc34581c8 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff63225b6481909217ad11b4f7d3ba |
completed | May 9, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_69ff60e0882c819085d097010db43ee0 |
completed | May 9, 2026, 4:29 p.m. |
Created at: May 3, 2026, 4:10 p.m.