Triple
T17924348
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tim Horton |
E448152
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object | Kelly Horton |
—
|
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: Kelly Horton | Statement: [Tim Horton, hasChild, Kelly Horton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kelly Horton Context triple: [Tim Horton, hasChild, Kelly Horton]
-
A.
Jennifer Horton
Jennifer Horton is a long-running fictional character on the American soap opera "Days of Our Lives," known as a member of the prominent Horton family and for her central romantic and dramatic storylines.
-
B.
Jeri-Lyn Horton
chosen
Jeri-Lyn Horton is a daughter of Canadian hockey legend and Tim Hortons co-founder Tim Horton.
-
C.
Tracy Horton
Tracy Horton is one of the children of Canadian hockey legend and Tim Hortons co-founder Tim Horton.
-
D.
Kelly Dixon
Kelly Dixon is a film editor best known for her work on major projects including the Marvel Studios sequel "Black Panther: Wakanda Forever."
-
E.
Kelly McCrimmon
Kelly McCrimmon is a Canadian ice hockey executive known for helping build the Vegas Golden Knights into a successful NHL franchise.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f79d14819095540856928f0e25 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4a54cf8188190b9bd676443418c23 |
completed | April 19, 2026, 9:50 a.m. |
Created at: April 10, 2026, 10:20 a.m.