Triple
T24606039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cropwell Bishop |
E608973
|
entity |
| Predicate | hasCheeseProducer |
P104672
|
FINISHED |
| Object | Cropwell Bishop Creamery |
—
|
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: Cropwell Bishop Creamery | Statement: [Cropwell Bishop, hasCheeseProducer, Cropwell Bishop Creamery]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCheeseProducer Context triple: [Cropwell Bishop, hasCheeseProducer, Cropwell Bishop Creamery]
-
A.
hasCheeseFactory
chosen
Indicates that an entity possesses, hosts, or contains a cheese-producing factory.
-
B.
hasCheeseStyleOrigin
Indicates that a cheese’s style or type originates from, or is traditionally associated with, a particular place or region.
-
C.
hasCheeseVarietyNamedAfterIt
Indicates that something has a type or variety of cheese that is named after it.
-
D.
cheeseMadeFrom
Indicates that one entity is produced or derived as cheese from another entity (typically a source ingredient such as milk).
-
E.
roleInCheese
Indicates that an entity participates in the production, composition, or classification of a cheese with a specific functional role.
- 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_69e2c4d060e08190ac9f7c49b1036e20 |
completed | April 17, 2026, 11:40 p.m. |
| NER | Named-entity recognition | batch_69f2be044d4c819094e14eda28d371a7 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6ca751c8190a040c10d701ecf3a |
completed | April 30, 2026, 12:48 a.m. |
Created at: April 18, 2026, 2:31 a.m.