Triple

T16635031
Position Surface form Disambiguated ID Type / Status
Subject Qimen County E404176 entity
Predicate knownFor P22 FINISHED
Object Keemun black tea E87033 NE 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: Keemun black tea | Statement: [Qimen County, knownFor, Keemun black tea]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keemun black tea
Context triple: [Qimen County, knownFor, Keemun black tea]
  • A. Keemun black tea chosen
    Keemun black tea is a renowned Chinese black tea variety prized for its rich, mellow flavor and aromatic, winey notes.
  • B. Darjeeling tea
    Darjeeling tea is a highly prized, aromatic black tea from the Himalayan foothills, celebrated for its delicate flavor, floral notes, and status as the “champagne of teas.”
  • C. Kangra tea
    Kangra tea is a distinctive variety of Indian tea from the Himalayan region of Himachal Pradesh, prized for its delicate flavor and aromatic quality.
  • D. Nilgiri tea
    Nilgiri tea is a fragrant, brisk black tea from India’s Nilgiri Hills, valued for its bright liquor and smooth, aromatic flavor.
  • E. Assam tea
    Assam tea is a robust, malty black tea variety grown in India’s northeastern Assam region, renowned worldwide for its strong flavor and use in breakfast blends like English and Irish Breakfast tea.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d8838a41f08190b0c3f79c47df5078 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e378e8a76c8190bf08e6f6dec63c50 completed April 18, 2026, 12:28 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0084b984d081909f76ef874431ff40 completed May 10, 2026, 1:14 p.m.
Created at: April 10, 2026, 5:17 a.m.