Triple
T13196251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ashley Eriksson |
E314118
|
entity |
| Predicate | recordLabel |
P1500
|
FINISHED |
| Object | K Records |
E80871
|
NE FINISHED |
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: K Records | Statement: [Ashley Eriksson, recordLabel, K Records]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: K Records Context triple: [Ashley Eriksson, recordLabel, K Records]
-
A.
K Records
chosen
K Records is an independent record label based in Olympia, Washington, known for its influential role in the DIY, indie rock, and lo-fi music scenes.
-
B.
Bedrock Records
Bedrock Records is a prominent UK electronic music label co-founded by John Digweed, known for its influential progressive house and techno releases.
-
C.
Streamline Records
Streamline Records is a record label associated with major pop acts, notably helping launch the early career of American singer-songwriter Lady Gaga.
-
D.
Brando Records
Brando Records is an independent music label known for working with alternative rock acts such as Blue October.
-
E.
One Records
One Records is a music label known for releasing hip-hop projects, including work by rapper Fashawn.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d806ae1e08819090d95bfe1538cc17 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98c626058819086f604b11af2d4eb |
completed | April 10, 2026, 11:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f72662a7088190b0aacc47b37390f4 |
completed | May 3, 2026, 10:41 a.m. |
Created at: April 9, 2026, 9:16 p.m.