Triple
T23253817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soul II Soul |
E581809
|
entity |
| Predicate | recordLabel |
P1500
|
FINISHED |
| Object | 10 Records |
—
|
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: 10 Records | Statement: [Soul II Soul, recordLabel, 10 Records]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 10 Records Context triple: [Soul II Soul, recordLabel, 10 Records]
-
A.
10 Records
chosen
10 Records was a British record label active primarily in the 1980s, known for releasing pop and rock music from various UK and international artists.
-
B.
Record Records
Record Records is an Icelandic independent record label known for releasing music by artists such as Of Monsters and Men.
-
C.
Beyond Records
Beyond Records is a music record label known for releasing the album "No Exit."
-
D.
10 Over 10
"10 Over 10" is a popular hip-hop track by Nigerian rapper Naeto C, celebrated for its catchy hook and club-friendly production.
-
E.
10 on Ten
10 on Ten is a 2004 documentary film by acclaimed Iranian director Abbas Kiarostami in which he reflects on the art and practice of filmmaking through ten lessons.
- 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_69e24606b17c81908aba1a4911c8a8ba |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f193f9d904819097315c9bf031f667 |
completed | April 29, 2026, 5:15 a.m. |
Created at: April 17, 2026, 4:11 p.m.