Triple

T7418277
Position Surface form Disambiguated ID Type / Status
Subject Prism E171181 entity
Predicate track P17929 FINISHED
Object Dark Horse E171171 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: Dark Horse | Statement: [Prism, track, Dark Horse]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dark Horse
Context triple: [Prism, track, Dark Horse]
  • A. Dark Horse chosen
    "Dark Horse" is a 2013 trap-pop and hip hop-influenced song by American singer Katy Perry featuring rapper Juicy J that became a global hit and one of her signature tracks.
  • B. Dark Horse
    Dark Horse is a modern, track-focused high-performance variant of the Ford Mustang designed to deliver enhanced power, handling, and racing capability.
  • C. Dark Horse
    "Dark Horse" is a rapid-fire hip-hop track by Chicago rapper Twista, showcasing his signature fast-paced lyrical delivery.
  • D. Darkhorse
    Darkhorse is the storied nickname of the U.S. Marine Corps’ 3rd Battalion, 5th Marines, renowned for its combat service and battlefield sacrifices.
  • E. Black Horse
    Black Horse is a UK-based finance company best known for providing motor and other consumer finance services as part of the Lloyds Banking Group.
  • 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_69c68a625d048190af70eb8b63bec5a0 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f2c9314c8190855b79a2e6ef3e9b completed March 27, 2026, 9:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8277c92788190bcd36cfa461b4d95 completed March 28, 2026, 7:09 p.m.
Created at: March 27, 2026, 3:11 p.m.