Triple

T14527494
Position Surface form Disambiguated ID Type / Status
Subject Shan Yu E340816 entity
Predicate defeatedBy P11263 FINISHED
Object Khan (Mulan's horse)
Khan is the loyal, comedic, and brave black horse who serves as Mulan’s primary animal companion and mount in Disney’s animated film "Mulan."
 E1103874 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: Khan (Mulan's horse) | Statement: [Shan Yu, defeatedBy, Khan (Mulan's horse)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Khan (Mulan's horse)
Context triple: [Shan Yu, defeatedBy, Khan (Mulan's horse)]
  • A. Dala horse
    The Dala horse is a traditional carved and painted wooden horse from Sweden, widely recognized as a national folk art icon and symbol of Swedish heritage.
  • B. Uslan
    Uslan is a surname most notably associated with Michael Uslan, the American film producer and comic book historian behind the modern Batman movie franchise.
  • C. Mahaba
    Mahaba is a popular song by Tanzanian Bongo Flava artist Ali Kiba, known for its romantic theme and melodic style.
  • D. Luilang
    Luilang is an extinct Austronesian language once spoken by an indigenous group in northern Taiwan.
  • E. Cavalla
    Cavalla is a historic port city on the Aegean Sea in northern Greece, known today as Kavala and noted for its strategic location and Ottoman-era heritage.
  • 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: Khan (Mulan's horse)
Triple: [Shan Yu, defeatedBy, Khan (Mulan's horse)]
Generated description
Khan is the loyal, comedic, and brave black horse who serves as Mulan’s primary animal companion and mount in Disney’s animated film "Mulan."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Khan (Mulan's horse)
Target entity description: Khan is the loyal, comedic, and brave black horse who serves as Mulan’s primary animal companion and mount in Disney’s animated film "Mulan."
  • A. Dala horse
    The Dala horse is a traditional carved and painted wooden horse from Sweden, widely recognized as a national folk art icon and symbol of Swedish heritage.
  • B. Uslan
    Uslan is a surname most notably associated with Michael Uslan, the American film producer and comic book historian behind the modern Batman movie franchise.
  • C. Mahaba
    Mahaba is a popular song by Tanzanian Bongo Flava artist Ali Kiba, known for its romantic theme and melodic style.
  • D. Luilang
    Luilang is an extinct Austronesian language once spoken by an indigenous group in northern Taiwan.
  • E. Cavalla
    Cavalla is a historic port city on the Aegean Sea in northern Greece, known today as Kavala and noted for its strategic location and Ottoman-era heritage.
  • 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_69d822dac79c8190a84a073f3cbaced5 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dea051bc608190ad4d516c5e7bca43 completed April 14, 2026, 8:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd7a52260881909a0d85603666107d completed May 8, 2026, 5:53 a.m.
NEDg Description generation batch_69fd7b58096881909d85a2b319acb595 completed May 8, 2026, 5:57 a.m.
NED2 Entity disambiguation (via description) batch_69fd7bd58a6881908479b7608b7f1f3a completed May 8, 2026, 5:59 a.m.
Created at: April 10, 2026, 1:22 a.m.