Triple
T22259241
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brittany Runs a Marathon |
E550174
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Keegan DeWitt |
—
|
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: Keegan DeWitt | Statement: [Brittany Runs a Marathon, musicBy, Keegan DeWitt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Keegan DeWitt Context triple: [Brittany Runs a Marathon, musicBy, Keegan DeWitt]
-
A.
Keegan DeWitt
chosen
Keegan DeWitt is an American composer and musician known for his atmospheric film scores and indie music collaborations.
-
B.
Drew Sheehan
Drew Sheehan is a character in the television series "Mare of Easttown," known as the young grandson of the main character, Mare Sheehan.
-
C.
Jordan Cavanaugh
Jordan Cavanaugh is the brilliant, headstrong forensic pathologist who serves as the central protagonist of the crime drama television series "Crossing Jordan."
-
D.
Drew Kirsch
Drew Kirsch is an American music video director known for his visually inventive work with major pop and rock artists.
-
E.
Dawson Scott
Dawson Scott is the surname of Catherine Amy Dawson Scott, a British writer and co-founder of the international writers’ organization PEN.
- 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_69e11e42adb8819087714772ea606709 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f138c5b54c8190854690ba599639fa |
completed | April 28, 2026, 10:46 p.m. |
Created at: April 16, 2026, 8:39 p.m.