Triple
T34083746
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marries former escort Willa Ferreyra |
E874119
|
entity |
| Predicate | hasGroomHalfSibling |
P181376
|
FINISHED |
| Object | Kendall Roy |
—
|
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: Kendall Roy | Statement: [Marries former escort Willa Ferreyra, hasGroomHalfSibling, Kendall Roy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGroomHalfSibling Context triple: [Marries former escort Willa Ferreyra, hasGroomHalfSibling, Kendall Roy]
-
A.
hasHalfSibling
Indicates that two individuals share exactly one biological parent in common, making them half-siblings.
-
B.
hasHalfBrother
Indicates that one person has a male sibling with whom they share exactly one biological parent.
-
C.
spouseIsHalfSisterOf
Indicates that the person’s spouse is also their half-sister, sharing exactly one biological parent with them.
-
D.
hasNephewByMarriage
Indicates that one person is the nephew of another person through marriage rather than by blood.
-
E.
hasGroomFather
Indicates that a person serves as the father of the groom in a marriage-related relationship.
- 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_69f349a61d448190b74642f325d3eb7a |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f7688dd3d08190ad13d0e780570a1c |
completed | May 3, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_69f767fcf2f881908bacc7bfc38e68a5 |
completed | May 3, 2026, 3:21 p.m. |
| PDg | Predicate description generation | batch_69f7688cea58819098bdfd7c80df7634 |
completed | May 3, 2026, 3:23 p.m. |
Created at: May 1, 2026, 1:52 a.m.