Triple
T34083744
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marries former escort Willa Ferreyra |
E874119
|
entity |
| Predicate | hasGroomFamily |
P149460
|
FINISHED |
| Object | Roy family |
—
|
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: Roy family | Statement: [Marries former escort Willa Ferreyra, hasGroomFamily, Roy family]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGroomFamily Context triple: [Marries former escort Willa Ferreyra, hasGroomFamily, Roy family]
-
A.
hasGroom
Indicates that an entity has a groom, i.e., is associated with a male partner in a marriage or wedding relationship.
-
B.
brideFamily
chosen
Indicates a familial relationship in which one party is the family or relatives of the bride in a marriage context.
-
C.
hasMainCouple
Indicates that a work or narrative features a primary romantic couple who are the central focus of its relationship storyline.
-
D.
associatedWithWeddingOf
Indicates a relationship where something is connected or related to the wedding event of specific individuals.
-
E.
hasFamilyOrganization
Indicates that an entity is associated with, belongs to, or is structured within a particular family-based organizational unit or system.
- 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_69f7626667f48190ad90867eb67ec582 |
completed | May 3, 2026, 2:57 p.m. |
| PD | Predicate disambiguation | batch_69f76175d6608190b60b268e20f49ed9 |
completed | May 3, 2026, 2:53 p.m. |
Created at: May 1, 2026, 1:52 a.m.