Triple
T27668987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cigarettes & Alcohol |
E697309
|
entity |
| Predicate | labelCatalogNumberUKCD |
P34455
|
FINISHED |
| Object | CRESCD 190 |
—
|
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: CRESCD 190 | Statement: [Cigarettes & Alcohol, labelCatalogNumberUKCD, CRESCD 190]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: labelCatalogNumberUKCD Context triple: [Cigarettes & Alcohol, labelCatalogNumberUKCD, CRESCD 190]
-
A.
classificationByUK
Indicates a relationship where an entity is assigned a category, status, or type according to a United Kingdom–specific classification system.
-
B.
labelCatalog
Indicates assigning or associating a descriptive label or identifier with a catalog entity or catalog entry.
-
C.
recordLabelCatalogNumber
chosen
Indicates the catalog or identification number assigned to a release by a record label.
-
D.
hasUKVersion
Indicates that an entity has a corresponding version or variant that is specific to the United Kingdom.
-
E.
alternativeCatalogNumber
Indicates that an entity is associated with an additional or substitute catalog number different from its primary catalog identifier.
- 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_69ef590b85a4819083ec7c12bd3c9c10 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f634a6a11481908066bcb7b4c656b1 |
completed | May 2, 2026, 5:30 p.m. |
| PD | Predicate disambiguation | batch_69f62c1a92648190835a2c5250d8c758 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:40 p.m.