Triple
T19521362
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crossroads |
E488407
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Trevor Jones |
—
|
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: Trevor Jones | Statement: [Crossroads, musicBy, Trevor Jones]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Trevor Jones Context triple: [Crossroads, musicBy, Trevor Jones]
-
A.
Trevor Jones
chosen
Trevor Jones is a South African-born film composer known for his work on numerous prominent movie scores, including the romantic comedy "Notting Hill."
-
B.
Denny Matthews
Denny Matthews is a longtime radio play-by-play announcer best known as the iconic voice of the Kansas City Royals.
-
C.
Jason Dooley
Jason Dooley is a musician best known as a performer associated with the band Born of You.
-
D.
Brent Jones
Brent Jones is a former NFL tight end best known for his successful career with the San Francisco 49ers, where he became a multiple-time Pro Bowler and three-time Super Bowl champion.
-
E.
Brant Tucker
Brant Tucker is a fictional character appearing in the DC Comics series "The Sandman," specifically in the "Worlds' End" story arc.
- 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_69d8e8da8bec819081f400199491ccc3 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e635a0b37c8190b70b7427c2e85f59 |
completed | April 20, 2026, 2:18 p.m. |
Created at: April 10, 2026, 1:40 p.m.