Triple
T21823632
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LA to Vegas |
E538791
|
entity |
| Predicate | starred |
P5563
|
FINISHED |
| Object | Kim Matula |
—
|
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: Kim Matula | Statement: [LA to Vegas, starred, Kim Matula]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kim Matula Context triple: [LA to Vegas, starred, Kim Matula]
-
A.
Kim Matula
chosen
Kim Matula is an American actress best known for her role on the long-running soap opera "The Bold and the Beautiful."
-
B.
Chris Mara
Chris Mara is an American football executive best known as a senior personnel executive and longtime member of the ownership family of the New York Giants.
-
C.
Kim Martin
Kim Martin is a television executive best known for her role as executive producer of the popular Food Network competition series "Beat Bobby Flay."
-
D.
Paul Kimatian
Paul Kimatian is a screenwriter best known for his work on the gambling-themed film "Deuces Wild."
-
E.
Josh Muscatine
Josh Muscatine is a film editor best known for his work on the thriller sequel "Wild Things 2."
- 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_69e0c475038c8190abb9b1a20eb8ff50 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f0912f69f08190b06c718aa35c2bf0 |
completed | April 28, 2026, 10:51 a.m. |
Created at: April 16, 2026, 6:54 p.m.