Triple
T28275042
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elise Eliot Atchison |
E712963
|
entity |
| Predicate | relationshipToBill Atchison |
P143942
|
FINISHED |
| Object | ex-wife |
—
|
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: ex-wife | Statement: [Elise Eliot Atchison, relationshipToBill Atchison, ex-wife]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relationshipToBill Atchison Context triple: [Elise Eliot Atchison, relationshipToBill Atchison, ex-wife]
-
A.
relationshipWithBill
chosen
Indicates that there exists some specified type of relationship or association between an entity and Bill.
-
B.
relationshipTypeWithBillHenrickson
Indicates the specific nature or category of relationship an entity has with Bill Henrickson.
-
C.
relationshipTypeWithGoosefatBill
Indicates the specific nature or category of relationship that an entity has with GoosefatBill.
-
D.
relationshipToBillAnderson
Indicates the specific familial, social, or professional relationship that one entity has to the person Bill Anderson.
-
E.
relationshipToState
Indicates a relationship or connection that an entity has with a particular state or governmental body.
- 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_69efb52275788190ae5181ccebef18ce |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69ffed8912488190baa05f572e5b1b89 |
completed | May 10, 2026, 2:29 a.m. |
| PD | Predicate disambiguation | batch_69ffed12a76c8190ad85c6ac869c72e9 |
completed | May 10, 2026, 2:27 a.m. |
Created at: April 27, 2026, 11:19 p.m.