Triple

T18418184
Position Surface form Disambiguated ID Type / Status
Subject Juddmonte Farms E441949 entity
Predicate notableHorseOwned P55479 FINISHED
Object Rail Link 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: Rail Link | Statement: [Juddmonte Farms, notableHorseOwned, Rail Link]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rail Link
Context triple: [Juddmonte Farms, notableHorseOwned, Rail Link]
  • A. Rail Link chosen
    Rail Link is a British-bred Thoroughbred racehorse best known for winning the 2006 Prix de l'Arc de Triomphe.
  • B. Express Rail Link
    Express Rail Link is a high-speed rail service in Malaysia that connects Kuala Lumpur International Airport with central Kuala Lumpur.
  • C. Railink
    Railink is an Indonesian railway company best known for operating airport rail link services connecting major airports with city centers.
  • D. Airport Rail Link
    The Airport Rail Link is a rapid transit rail line in Bangkok that connects the city center with Suvarnabhumi Airport, providing a fast alternative to road travel.
  • E. UP Express rail link
    The UP Express rail link is a dedicated airport rail service in Toronto that connects Toronto Pearson International Airport with the city's downtown Union Station.
  • 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_69d8b9eb8a508190a942fd75ebd8b1dc completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e51a291f148190b289b5b617077797 completed April 19, 2026, 6:08 p.m.
Created at: April 10, 2026, 10:47 a.m.