Triple
T28071190
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mull of Kintyre |
E709403
|
entity |
| Predicate | salesUK |
P160045
|
FINISHED |
| Object | over 2 million copies |
—
|
LITERAL 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: over 2 million copies | Statement: [Mull of Kintyre, salesUK, over 2 million copies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: salesUK Context triple: [Mull of Kintyre, salesUK, over 2 million copies]
-
A.
salesUK
chosen
Indicates that a sales-related activity, transaction, or performance metric is specifically associated with the United Kingdom.
-
B.
salesUS
Indicates a relationship where sales activity, revenue, or transactions are specifically associated with the United States.
-
C.
sharePurchaseByUK
Indicates that a purchase of shares is made by a UK-based entity or person.
-
D.
salesWorldwide
Indicates a relationship where an entity’s sales figures or activities are measured, reported, or occur across multiple countries or global markets.
-
E.
statusInUK
Indicates the legal or official status that an entity holds within the United Kingdom (e.g., immigration, residency, or authorization category).
- F. None of above.
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_69ef9b6f8078819098b741274cd1a2ee |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f6403ca9a081908446eafd52a0c7b3 |
completed | May 2, 2026, 6:19 p.m. |
| PD | Predicate disambiguation | batch_69f637120c008190b2b5adf46f022e48 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 8:46 p.m.