Triple

T21730535
Position Surface form Disambiguated ID Type / Status
Subject Christmas Hurdle E536391 entity
Predicate notableWinner P2766 FINISHED
Object Harchibald
Harchibald was a high-class National Hunt racehorse best known as a brilliant but quirky hurdler who captured several major Grade 1 races in the mid-2000s.
 E1500277 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: Harchibald | Statement: [Christmas Hurdle, notableWinner, Harchibald]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Harchibald
Context triple: [Christmas Hurdle, notableWinner, Harchibald]
  • A. Archbald
    Archbald is a small borough in Lackawanna County, northeastern Pennsylvania, known as a residential community within the Scranton–Wilkes-Barre metropolitan area.
  • B. Malkolm
    Malkolm is a less common variant spelling of the surname Malcolm, which has Scottish origins.
  • C. Geoffrey
    Geoffrey is a masculine given name of English origin, famously borne by pioneering computer scientist and AI researcher Geoffrey Hinton.
  • D. Geoffrey
    Geoffrey was a medieval English prince, one of the sons of King Henry II of England and Eleanor of Aquitaine.
  • E. Hugh Morrus
    Hugh Morrus is the ring name of Bill DeMott, a former professional wrestler best known for his work in WCW and WWE and later as a controversial trainer and coach.
  • 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: Harchibald
Triple: [Christmas Hurdle, notableWinner, Harchibald]
Generated description
Harchibald was a high-class National Hunt racehorse best known as a brilliant but quirky hurdler who captured several major Grade 1 races in the mid-2000s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Harchibald
Target entity description: Harchibald was a high-class National Hunt racehorse best known as a brilliant but quirky hurdler who captured several major Grade 1 races in the mid-2000s.
  • A. Archbald
    Archbald is a small borough in Lackawanna County, northeastern Pennsylvania, known as a residential community within the Scranton–Wilkes-Barre metropolitan area.
  • B. Malkolm
    Malkolm is a less common variant spelling of the surname Malcolm, which has Scottish origins.
  • C. Geoffrey
    Geoffrey is a masculine given name of English origin, famously borne by pioneering computer scientist and AI researcher Geoffrey Hinton.
  • D. Geoffrey
    Geoffrey was a medieval English prince, one of the sons of King Henry II of England and Eleanor of Aquitaine.
  • E. Hugh Morrus
    Hugh Morrus is the ring name of Bill DeMott, a former professional wrestler best known for his work in WCW and WWE and later as a controversial trainer and coach.
  • 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_69e0c46d3284819099a4f9d5a704eb95 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69effd064fcc819084852b4248f65a81 completed April 28, 2026, 12:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0a2ece628c8190b189516764b2ecdb completed May 17, 2026, 9:10 p.m.
NEDg Description generation batch_6a0a32fb6c2c81908ecdcf3acad3cf36 completed May 17, 2026, 9:28 p.m.
NED2 Entity disambiguation (via description) batch_6a0a33b435e08190a595c32a3747d1fd completed May 17, 2026, 9:31 p.m.
Created at: April 16, 2026, 6:48 p.m.