Triple
T19936082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leonard Cohen discography |
E479178
|
entity |
| Predicate | includes |
P1393
|
FINISHED |
| Object | Live Songs |
—
|
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: Live Songs | Statement: [Leonard Cohen discography, includes, Live Songs]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Live Songs Context triple: [Leonard Cohen discography, includes, Live Songs]
-
A.
Live Songs
chosen
Live Songs is a 1973 live album by Leonard Cohen featuring concert recordings that reinterpret many of his early songs with raw, intimate performances.
-
B.
Live!
Live! is a jazz album by organist Jack McDuff, capturing his energetic soul-jazz style in a live performance setting.
-
C.
Live!
Live! is a landmark 1975 live reggae album by Bob Marley and the Wailers, celebrated for its energetic performances and iconic recording of "No Woman, No Cry."
-
D.
Live
Live is a concert album by avant-garde metal band Sleepytime Gorilla Museum, capturing their experimental and theatrical performances in a live setting.
-
E.
Live
Live is an American rock band best known for their 1994 multi-platinum album "Throwing Copper" and hit singles like "Lightning Crashes."
- 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_69d8e522a17c819095165d4d24939fd8 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65a173a448190a25cb859803e3afc |
completed | April 20, 2026, 4:53 p.m. |
Created at: April 10, 2026, 1:53 p.m.