Triple

T22548239
Position Surface form Disambiguated ID Type / Status
Subject Distell Group E557486 entity
Predicate owns P347 FINISHED
Object Hunter's Dry 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: Hunter's Dry | Statement: [Distell Group, owns, Hunter's Dry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hunter's Dry
Context triple: [Distell Group, owns, Hunter's Dry]
  • A. Hunter's Dry chosen
    Hunter's Dry is a popular South African cider brand known for its crisp, refreshing taste and wide availability.
  • B. The Happy Hunting Ground
    "The Happy Hunting Ground" is a song featured on the soundtrack of the 1973 British satirical film *O Lucky Man!*, composed and performed by Alan Price.
  • C. Hunter Hunter
    Hunter Hunter is a 2020 Canadian survival horror thriller film about a fur trapper’s family in the remote wilderness being stalked by a mysterious predator.
  • D. Hunter's Light
    Hunter's Light is a Godolphin-owned Thoroughbred racehorse best known for his international Group 1 victories on turf and synthetic surfaces.
  • E. The Hunter
    The Hunter is a 1962 crime novel by Donald E. Westlake (writing as Richard Stark), introducing the ruthless professional thief Parker in a hardboiled tale of betrayal and revenge.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e58662081909ae346ab384514ca completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15f372df48190ae5dd461b1230bc7 completed April 29, 2026, 1:30 a.m.
Created at: April 16, 2026, 8:52 p.m.