Triple
T20168700
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crazy Horse |
E491895
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Sleeps with Angels |
—
|
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: Sleeps with Angels | Statement: [Crazy Horse, notableWork, Sleeps with Angels]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sleeps with Angels Context triple: [Crazy Horse, notableWork, Sleeps with Angels]
-
A.
Sleeps with Angels
chosen
Sleeps with Angels is a 1994 studio album by Neil Young and Crazy Horse known for its dark, reflective tone and elegiac themes.
-
B.
Footsteps of Angels
Footsteps of Angels is a lyric poem by Henry Wadsworth Longfellow that reflects on memory, loss, and the comforting presence of departed loved ones.
-
C.
The Trouble with Angels
The Trouble with Angels is a 1966 comedy film about two mischievous girls at a Catholic boarding school, starring Hayley Mills and directed by Ida Lupino.
-
D.
Like the Angel
"Like the Angel" is a politically charged melodic hardcore song by Rise Against from their album "Revolutions per Minute."
-
E.
Once an Angel
"Once an Angel" is a song featured on the album "Lucky Thirteen."
- 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_69da6266c6888190bc1a3ecf24814d34 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e66846f4ec81908b0dc6a6e0ec27dd |
completed | April 20, 2026, 5:54 p.m. |
Created at: April 11, 2026, 11:35 p.m.