Triple

T18110939
Position Surface form Disambiguated ID Type / Status
Subject Nunthorpe Stakes E433470 entity
Predicate notableWinner P2766 FINISHED
Object Tagula
Tagula is a British Thoroughbred racehorse best known for his Group 1-winning performances as a top-class sprinter in the mid-1990s.
E1307201 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: Tagula | Statement: [Nunthorpe Stakes, notableWinner, Tagula]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tagula
Context triple: [Nunthorpe Stakes, notableWinner, Tagula]
  • A. Songololo
    Songololo is a town in the western Democratic Republic of the Congo, situated near the border with Angola and known as a local transport and trade hub.
  • B. Tatumbla
    Tatumbla is a small town and municipality located in the central Honduran highlands within the Francisco Morazán Department.
  • C. Umbundu
    Umbundu is a major Bantu language spoken primarily in central and southern Angola, especially by the Ovimbundu people.
  • D. Mbanderu
    Mbanderu is a subgroup of the Herero people with its own distinct dialect and cultural traditions, primarily found in Namibia and Botswana.
  • E. Zingara
    Zingara is a fictional seafaring kingdom of skilled swordsmen and pirates in Robert E. Howard’s Hyborian Age, best known from the Conan the Barbarian stories.
  • 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: Tagula
Triple: [Nunthorpe Stakes, notableWinner, Tagula]
Generated description
Tagula is a British Thoroughbred racehorse best known for his Group 1-winning performances as a top-class sprinter in the mid-1990s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tagula
Target entity description: Tagula is a British Thoroughbred racehorse best known for his Group 1-winning performances as a top-class sprinter in the mid-1990s.
  • A. Songololo
    Songololo is a town in the western Democratic Republic of the Congo, situated near the border with Angola and known as a local transport and trade hub.
  • B. Tatumbla
    Tatumbla is a small town and municipality located in the central Honduran highlands within the Francisco Morazán Department.
  • C. Umbundu
    Umbundu is a major Bantu language spoken primarily in central and southern Angola, especially by the Ovimbundu people.
  • D. Mbanderu
    Mbanderu is a subgroup of the Herero people with its own distinct dialect and cultural traditions, primarily found in Namibia and Botswana.
  • E. Zingara
    Zingara is a fictional seafaring kingdom of skilled swordsmen and pirates in Robert E. Howard’s Hyborian Age, best known from the Conan the Barbarian stories.
  • 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_69d8b90916008190a1f110bd7ced5473 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4ddd2038081909515fb6d17495cbf completed April 19, 2026, 1:51 p.m.
NED1 Entity disambiguation (via context triple) batch_6a037c3930e0819083b2355a0af67b72 completed May 12, 2026, 7:15 p.m.
NEDg Description generation batch_6a037dc3a150819085368bcf620e8768 completed May 12, 2026, 7:21 p.m.
NED2 Entity disambiguation (via description) batch_6a037e99ae98819087afa088fb42e847 completed May 12, 2026, 7:25 p.m.
Created at: April 10, 2026, 10:28 a.m.