Triple

T16809565
Position Surface form Disambiguated ID Type / Status
Subject South Down E408571 entity
Predicate previousConstituency P16751 FINISHED
Object Down E114965 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: Down | Statement: [South Down, previousConstituency, Down]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Down
Context triple: [South Down, previousConstituency, Down]
  • A. Down chosen
    Down is a historic county in Northern Ireland known for its coastal landscapes, the Mourne Mountains, and its role in Irish and British history.
  • B. Down
    "Down" is a 2009 R&B-pop single by British singer Jay Sean featuring Lil Wayne that became an international hit and topped the US Billboard Hot 100.
  • C. Down
    Down is a 1994 noise rock album by The Jesus Lizard, noted for its abrasive sound, dark humor, and influential place in the American underground rock scene.
  • D. Down
    "Down" is a melodic, emotionally driven rock song by Blink-182 known for its atmospheric sound and introspective lyrics.
  • E. Bottom
    Bottom is a section or movement within Arthur Rimbaud’s poetic cycle "Les Illuminations," known for its vivid, experimental imagery and symbolist style.
  • 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_69d88393905081908d00a86b99996ac8 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b2ceab608190a9c8cd339ddbea0a completed April 18, 2026, 4:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00b290d8e4819082880444b42ffa43 completed May 10, 2026, 4:30 p.m.
Created at: April 10, 2026, 5:23 a.m.