Triple
T8404351
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles Spencer-Churchill, 9th Duke of Marlborough |
E198455
|
entity |
| Predicate | spouseBackground |
P81820
|
FINISHED |
| Object | heiress to the Vanderbilt fortune |
—
|
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: heiress to the Vanderbilt fortune | Statement: [Charles Spencer-Churchill, 9th Duke of Marlborough, spouseBackground, heiress to the Vanderbilt fortune]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spouseBackground Context triple: [Charles Spencer-Churchill, 9th Duke of Marlborough, spouseBackground, heiress to the Vanderbilt fortune]
-
A.
spouseFamily
Indicates a family relationship formed through marriage, such as between a person and their spouse’s relatives.
-
B.
spouseAssociatedWith
Indicates a marital or spousal relationship or close association between two entities.
-
C.
spouse
Indicates that two entities are married to each other in a legally or socially recognized partnership.
-
D.
spouseFrom
Indicates that one person is the spouse of another person originating from a specified place or source.
-
E.
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).
- 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_69ca8310df9c8190b25f16161cca3e41 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cb83116bf48190894bd5d5465520ef |
completed | March 31, 2026, 8:17 a.m. |
| PD | Predicate disambiguation | batch_69cb70d473dc8190af8ea81ee5aa970d |
completed | March 31, 2026, 6:59 a.m. |
| PDg | Predicate description generation | batch_69cb76da264881909483b835e1db06da |
completed | March 31, 2026, 7:25 a.m. |
Created at: March 30, 2026, 6:05 p.m.