Triple
T23519005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Per Una |
E574449
|
entity |
| Predicate | soldExclusivelyThrough |
P108737
|
FINISHED |
| Object | Marks & Spencer |
—
|
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: Marks & Spencer | Statement: [Per Una, soldExclusivelyThrough, Marks & Spencer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: soldExclusivelyThrough Context triple: [Per Una, soldExclusivelyThrough, Marks & Spencer]
-
A.
brandExclusive
chosen
Indicates that something is restricted to, offered only by, or uniquely associated with a single brand.
-
B.
soldAt
Indicates that a product or item is offered for sale at a particular location, venue, or outlet.
-
C.
soldFrom
Indicates that something was transferred in a sale originating from a particular source, such as a seller, location, or organization.
-
D.
exclusiveTradingPostOf
Indicates a trading post that is dedicated to and used exclusively by a specific entity, with no other entities sharing its use.
-
E.
exclusiveAtLaunch
Indicates that an item was available only through a specific platform, channel, or partner during its initial launch period.
- 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_69e245bb3dcc8190ba9a2b35972b58d0 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1aa84fe7c8190aa1078a118af7d61 |
completed | April 29, 2026, 6:51 a.m. |
| PD | Predicate disambiguation | batch_69f06213e8c48190b52a7789fb91e02d |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 6:08 p.m.