Triple

T2934690
Position Surface form Disambiguated ID Type / Status
Subject Super Mario Bros. 3 E79236 entity
Predicate enemy P4567 FINISHED
Object Lakitu
Lakitu is a recurring cloud-riding Koopa in the Super Mario series known for hovering above the player and attacking by throwing Spiny eggs.
 E311692 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: Lakitu | Statement: [Super Mario Bros. 3, enemy, Lakitu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lakitu
Context triple: [Super Mario Bros. 3, enemy, Lakitu]
  • A. Lotso
    Lotso is the strawberry-scented teddy bear who serves as the main antagonist in Pixar's animated film Toy Story 3.
  • B. Kohunlich
    Kohunlich is a large Maya archaeological site in southern Quintana Roo, Mexico, noted for its monumental architecture and well-preserved stucco masks.
  • C. Liluah
    Liluah is a suburban locality in the Howrah district of West Bengal, India, known for its residential areas and railway facilities near Kolkata.
  • D. The Turim
    The Turim is a foundational 14th-century Jewish legal code by Rabbi Jacob ben Asher that systematically organizes halakhic rulings into four major sections.
  • E. Wonokitri
    Wonokitri is a village in East Java, Indonesia, known as a gateway settlement for visitors heading to the Mount Bromo area.
  • 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: Lakitu
Triple: [Super Mario Bros. 3, enemy, Lakitu]
Generated description
Lakitu is a recurring cloud-riding Koopa in the Super Mario series known for hovering above the player and attacking by throwing Spiny eggs.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lakitu
Target entity description: Lakitu is a recurring cloud-riding Koopa in the Super Mario series known for hovering above the player and attacking by throwing Spiny eggs.
  • A. Lotso
    Lotso is the strawberry-scented teddy bear who serves as the main antagonist in Pixar's animated film Toy Story 3.
  • B. Kohunlich
    Kohunlich is a large Maya archaeological site in southern Quintana Roo, Mexico, noted for its monumental architecture and well-preserved stucco masks.
  • C. Liluah
    Liluah is a suburban locality in the Howrah district of West Bengal, India, known for its residential areas and railway facilities near Kolkata.
  • D. The Turim
    The Turim is a foundational 14th-century Jewish legal code by Rabbi Jacob ben Asher that systematically organizes halakhic rulings into four major sections.
  • E. Wonokitri
    Wonokitri is a village in East Java, Indonesia, known as a gateway settlement for visitors heading to the Mount Bromo area.
  • 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_69ad8b0fbab081908f6a61567c045d8d completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad983c84688190aa7ed5b8091fb140 completed March 8, 2026, 3:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69b0867ba1b48190a54d00c32b075548 completed March 10, 2026, 9 p.m.
NEDg Description generation batch_69b0dbda7ab881908b5a3e1e897fcb49 completed March 11, 2026, 3:04 a.m.
NED2 Entity disambiguation (via description) batch_69b0dc3ed9e08190ac6c6357f0084ba6 completed March 11, 2026, 3:06 a.m.
Created at: March 8, 2026, 2:56 p.m.