Triple
T22499436
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brent Mydland |
E556228
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | “Far From Me” |
—
|
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: “Far From Me” | Statement: [Brent Mydland, notableWork, “Far From Me”]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: “Far From Me” Context triple: [Brent Mydland, notableWork, “Far From Me”]
-
A.
Far From Me
chosen
"Far From Me" is a song by the Grateful Dead featured on their 1980 studio album *Go to Heaven*.
-
B.
“Even When You’re Far Away”
“Even When You’re Far Away” is a track by the South Korean girl group GFriend from their EP *Season of Glass*.
-
C.
Away From Me
"Away From Me" is a 2003 post-grunge rock single by American band Puddle of Mudd, known for its heavy guitar riffs and emotionally charged lyrics.
-
D.
"Ten Feet Away"
"Ten Feet Away" is a country song recorded by Keith Whitley that became one of his signature hits in the mid-1980s.
-
E.
I Am Very Far
"I Am Very Far" is a 2011 studio album by the indie rock band Okkervil River, noted for its dense, expansive sound and ambitious songwriting.
- 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_69e11e5445bc8190b6a9481926db3355 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15cb4ff8c8190af0c60abafefe832 |
completed | April 29, 2026, 1:19 a.m. |
Created at: April 16, 2026, 8:50 p.m.