Triple

T5245226
Position Surface form Disambiguated ID Type / Status
Subject Ardbeg distillery E118441 entity
Predicate numberOfStills P62360 FINISHED
Object 2 wash stills 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: 2 wash stills | Statement: [Ardbeg distillery, numberOfStills, 2 wash stills]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: numberOfStills
Context triple: [Ardbeg distillery, numberOfStills, 2 wash stills]
  • A. filmStripCount
    Indicates the number of film strips associated with or contained in a given entity or context.
  • B. numberOfImagesReturned
    Indicates the total count of images that are produced or provided as the result of a query, request, or operation.
  • C. typicalStillType
    Indicates that something represents the usual or characteristic form, style, or configuration that an entity typically has or uses.
  • D. frontCameraCount
    Indicates the number of front-facing cameras associated with an entity.
  • E. rearCameraCount
    Indicates the number of camera units located on the rear side of a device.
  • F. None of above. chosen

Provenance (4 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_69bd4468aacc8190a8196f71855cdf4f completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7b515edc8190a9db198d4eb1c4f6 completed March 20, 2026, 4:52 p.m.
PD Predicate disambiguation batch_69bd77c1397c8190a7fd844d7a396e54 completed March 20, 2026, 4:37 p.m.
PDg Predicate description generation batch_69bd79e9d794819097bb628c603d14af completed March 20, 2026, 4:46 p.m.
Created at: March 20, 2026, 1:49 p.m.