Triple
T33973857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Margaret of Bavaria |
E871072
|
entity |
| Predicate | spouseOfHouse |
P195554
|
FINISHED |
| Object | House of Valois-Burgundy |
—
|
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: House of Valois-Burgundy | Statement: [Margaret of Bavaria, spouseOfHouse, House of Valois-Burgundy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spouseOfHouse Context triple: [Margaret of Bavaria, spouseOfHouse, House of Valois-Burgundy]
-
A.
spouseOfHead
Indicates that one person is the married partner of the individual who holds the position of head (e.g., head of a household, organization, or state).
-
B.
spouseOfType
Indicates that one entity is the spouse of another, specifying the type or role of that spousal relationship.
-
C.
spouseOfWork
Indicates that one person is the spouse of another specifically in the context of their workplace or professional environment.
-
D.
spouseOfCountry
Indicates that an entity is the spouse or marital partner of a person who is associated with, represents, or is from a specified country.
-
E.
spouseMember
Indicates that one entity is the spouse (married partner) of another entity.
- F. None of above. chosen
Provenance (4 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_69f3499da0188190ab1a4ff06fb06a2a |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fdd92396788190ae1424bc1ae55844 |
completed | May 8, 2026, 12:37 p.m. |
| PD | Predicate disambiguation | batch_69fdd678f40481909a717a2daec83b36 |
completed | May 8, 2026, 12:26 p.m. |
| PDg | Predicate description generation | batch_69fdd922d73c81908ad3faade247ec16 |
completed | May 8, 2026, 12:37 p.m. |
Created at: May 1, 2026, 1:50 a.m.