Triple
T34083740
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marries former escort Willa Ferreyra |
E874119
|
entity |
| Predicate | involvesRelationshipType |
P10690
|
FINISHED |
| Object | marriage |
—
|
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: marriage | Statement: [Marries former escort Willa Ferreyra, involvesRelationshipType, marriage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: involvesRelationshipType Context triple: [Marries former escort Willa Ferreyra, involvesRelationshipType, marriage]
-
A.
relationshipType
chosen
Indicates the specific kind of relationship that exists between two or more entities.
-
B.
inRelationshipWith
Indicates that two entities are mutually involved in a defined personal, romantic, or partnership relationship with each other.
-
C.
haveRelationshipWith
Indicates that one entity is in some form of defined relationship or association with another entity.
-
D.
coversRelationship
Indicates that one entity extends over, includes, or provides encompassing coverage for another entity or set of entities.
-
E.
relationshipTypeStart
Indicates the type or category of relationship that begins or is initiated at a specific point or event.
- 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_69f349a61d448190b74642f325d3eb7a |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69fd82ed2a4c81908bd7797fbd2e3d08 |
completed | May 8, 2026, 6:30 a.m. |
| PD | Predicate disambiguation | batch_69fd814cc10481908e4f8123d35a5d0c |
completed | May 8, 2026, 6:23 a.m. |
Created at: May 1, 2026, 1:52 a.m.