Triple
T19936282
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nick Cave and the Bad Seeds |
E479181
|
entity |
| Predicate | recordLabel |
P1500
|
FINISHED |
| Object | Bad Seed Ltd |
—
|
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: Bad Seed Ltd | Statement: [Nick Cave and the Bad Seeds, recordLabel, Bad Seed Ltd]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bad Seed Ltd Context triple: [Nick Cave and the Bad Seeds, recordLabel, Bad Seed Ltd]
-
A.
Bad Seed Ltd
chosen
Bad Seed Ltd is an independent record label founded by Nick Cave and the Bad Seeds to release their own music and related projects.
-
B.
Brevant Seeds
Brevant Seeds is an agricultural seed brand owned by Corteva Agriscience, offering a range of crop seed products to farmers.
-
C.
The Seed Cutters
"The Seed Cutters" is a poem by Seamus Heaney that reflects on rural Irish life and traditional agricultural labor through vivid, tactile imagery.
-
D.
Tuff Seed
"Tuff Seed" is a popular reggae/dancehall track by Ghanaian artist Stonebwoy that helped solidify his international recognition.
-
E.
Propeller Seeds
Propeller Seeds is a song by the British alternative rock band Sparks.
- 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.