Triple

T17791112
Position Surface form Disambiguated ID Type / Status
Subject Sussex Stakes E444162 entity
Predicate notableWinner P2766 FINISHED
Object Kris
Kris was a top-class British Thoroughbred racehorse of the late 1970s, renowned as one of the best milers of his generation.
 E1287925 NE FINISHED

How this triple was built (4 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: Kris | Statement: [Sussex Stakes, notableWinner, Kris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kris
Context triple: [Sussex Stakes, notableWinner, Kris]
  • A. Kris
    Kris is a novel by Swedish author Karin Boye, known for its introspective exploration of identity, faith, and inner conflict.
  • B. Kris
    Kris is an American daytime talk show hosted by Kris Jenner that briefly aired in 2013.
  • C. Kris
    Kris is a given name commonly used as a short or diminutive form of longer names such as Krista, Kristina, or Kristopher in various languages.
  • D. Kris
    Kris is the female playable protagonist introduced in Pokémon Crystal, recognized as one of the first customizable main characters in the Pokémon game series.
  • E. Kris
    Kris is the given name of English actor Kris Marshall, known for his roles in "Love Actually," "My Family," and various British television dramas and comedies.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Kris
Triple: [Sussex Stakes, notableWinner, Kris]
Generated description
Kris was a top-class British Thoroughbred racehorse of the late 1970s, renowned as one of the best milers of his generation.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kris
Target entity description: Kris was a top-class British Thoroughbred racehorse of the late 1970s, renowned as one of the best milers of his generation.
  • A. Kris
    Kris is the given name of English actor Kris Marshall, known for his roles in "Love Actually," "My Family," and various British television dramas and comedies.
  • B. Kris
    Kris is a novel by Swedish author Karin Boye, known for its introspective exploration of identity, faith, and inner conflict.
  • C. Kris
    Kris is an American daytime talk show hosted by Kris Jenner that briefly aired in 2013.
  • D. Kris
    Kris is the female playable protagonist introduced in Pokémon Crystal, recognized as one of the first customizable main characters in the Pokémon game series.
  • E. Kris
    Kris is a given name commonly used as a short or diminutive form of longer names such as Krista, Kristina, or Kristopher in various languages.
  • F. None of above. chosen

Provenance (5 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_69d8b9efe370819095cd219b143ae727 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e48797408081908c48d98e1525ae87 completed April 19, 2026, 7:43 a.m.
NED1 Entity disambiguation (via context triple) batch_6a02f83ab48c81909e42e1ed75efed29 completed May 12, 2026, 9:51 a.m.
NEDg Description generation batch_6a02f9af5dd08190896786ca9f8eb69f completed May 12, 2026, 9:58 a.m.
NED2 Entity disambiguation (via description) batch_6a02fa28ac0881909d9d4273ea576273 completed May 12, 2026, 10 a.m.
Created at: April 10, 2026, 10:13 a.m.