Triple
T33464872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joe Gargery |
E857017
|
entity |
| Predicate | treatmentBySpouse |
P51768
|
FINISHED |
| Object | is abused by Mrs. Joe Gargery |
—
|
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: is abused by Mrs. Joe Gargery | Statement: [Joe Gargery, treatmentBySpouse, is abused by Mrs. Joe Gargery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: treatmentBySpouse Context triple: [Joe Gargery, treatmentBySpouse, is abused by Mrs. Joe Gargery]
-
A.
throughSpouse
Indicates a relationship or connection that exists indirectly between two entities by way of one entity’s spouse.
-
B.
spouseAction
chosen
Indicates that one person performs an action toward or on their spouse within the context of a marital relationship.
-
C.
spouse
Indicates that two entities are married to each other in a legally or socially recognized partnership.
-
D.
spouseInvolvedIn
Indicates that a person's spouse participates in, is associated with, or plays a role in a specified activity, event, or situation.
-
E.
governedThroughSpouse
Indicates that one entity exercised governing authority or political power indirectly through their spouse, who held the formal ruling position.
- 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_69f34973461481909c701c98ebd75623 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7308a096081909d66a56f3c926806 |
completed | May 3, 2026, 11:24 a.m. |
| PD | Predicate disambiguation | batch_69f72a00c5f081908b6539d15baf4e12 |
completed | May 3, 2026, 10:57 a.m. |
Created at: May 1, 2026, 1:37 a.m.