Triple
T25496116
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ernest Aldrich Simpson |
E638970
|
entity |
| Predicate | formerHusbandOf |
P176255
|
FINISHED |
| Object | Wallis Simpson |
—
|
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: Wallis Simpson | Statement: [Ernest Aldrich Simpson, formerHusbandOf, Wallis Simpson]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerHusbandOf Context triple: [Ernest Aldrich Simpson, formerHusbandOf, Wallis Simpson]
-
A.
formerFiancéeOf
Indicates that one person was previously engaged to be married to another person, but the engagement has since ended.
-
B.
allegedSpouseOf
Indicates a relationship where one person is claimed or reported to be the spouse of another, but the marital status is not legally or definitively confirmed.
-
C.
spouseOfFormer
Indicates that one entity is the spouse of another entity who is a former holder of some role, status, or position.
-
D.
sometimesSpouseOf
Indicates that two entities are occasionally, but not consistently or permanently, in a spousal relationship with each other.
-
E.
firstHolderSpouseOf
Indicates that the first holder in the relation is the spouse (married partner) of the other holder.
- 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_69e75dbbd2a88190b70e1e645de14b9a |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f6dfcafd0c81908d86662948c539d6 |
completed | May 3, 2026, 5:40 a.m. |
| PD | Predicate disambiguation | batch_69f6de07836481908785cde9c511920b |
completed | May 3, 2026, 5:32 a.m. |
| PDg | Predicate description generation | batch_69f6df418f488190a5e7ff41f32dceda |
completed | May 3, 2026, 5:38 a.m. |
Created at: April 21, 2026, 2:40 p.m.