Triple

T6238772
Position Surface form Disambiguated ID Type / Status
Subject Gary Stevens E139542 entity
Predicate notableHorseRidden P55479 FINISHED
Object Da Hoss
Da Hoss was a celebrated American Thoroughbred racehorse best known for his remarkable two-time victory in the Breeders’ Cup Mile, achieved three years apart.
E577617 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: Da Hoss | Statement: [Gary Stevens, notableHorseRidden, Da Hoss]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Da Hoss
Context triple: [Gary Stevens, notableHorseRidden, Da Hoss]
  • A. Daule
    Daule is a town and canton in coastal Ecuador known for its rice production and location within the Guayas Province.
  • B. Hasana
    Hasana is a small town in Egypt’s North Sinai Governorate, situated in the Sinai Peninsula.
  • C. Haya
    Haya is a feminine given name of Arabic origin, commonly used in the Middle East and among Arabic-speaking communities.
  • D. Haiman
    Haiman is a surname and given name that serves as a variant form of "Hyman," often associated with individuals of Jewish heritage.
  • E. Hadda
    Hadda was an important ancient Buddhist monastic and artistic center in the Gandhara region, renowned for its rich collection of Greco-Buddhist sculptures and monasteries.
  • 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: Da Hoss
Triple: [Gary Stevens, notableHorseRidden, Da Hoss]
Generated description
Da Hoss was a celebrated American Thoroughbred racehorse best known for his remarkable two-time victory in the Breeders’ Cup Mile, achieved three years apart.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Da Hoss
Target entity description: Da Hoss was a celebrated American Thoroughbred racehorse best known for his remarkable two-time victory in the Breeders’ Cup Mile, achieved three years apart.
  • A. Daule
    Daule is a town and canton in coastal Ecuador known for its rice production and location within the Guayas Province.
  • B. Hasana
    Hasana is a small town in Egypt’s North Sinai Governorate, situated in the Sinai Peninsula.
  • C. Haya
    Haya is a feminine given name of Arabic origin, commonly used in the Middle East and among Arabic-speaking communities.
  • D. Haiman
    Haiman is a surname and given name that serves as a variant form of "Hyman," often associated with individuals of Jewish heritage.
  • E. Hadda
    Hadda was an important ancient Buddhist monastic and artistic center in the Gandhara region, renowned for its rich collection of Greco-Buddhist sculptures and monasteries.
  • 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_69c008b0e7ac8190808a59573ee646f3 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c063048df081909a13d16b6f6bf65d completed March 22, 2026, 9:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69c20e01845081909c54fe938600be3e completed March 24, 2026, 4:07 a.m.
NEDg Description generation batch_69c215ff293c8190a79dd9246c38880d completed March 24, 2026, 4:41 a.m.
NED2 Entity disambiguation (via description) batch_69c2167ef4748190bebcf28468a696bc completed March 24, 2026, 4:43 a.m.
Created at: March 22, 2026, 4:23 p.m.