Triple

T15534507
Position Surface form Disambiguated ID Type / Status
Subject Comet Observatory E370307 entity
Predicate primaryResident P75 FINISHED
Object Lumas
Lumas are small, star-like creatures in the Super Mario Galaxy series who accompany Rosalina and help power the Comet Observatory.
 E75273 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: Lumas | Statement: [Comet Observatory, primaryResident, Lumas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lumas
Context triple: [Comet Observatory, primaryResident, Lumas]
  • A. Lumo
    Lumo is a British open-access train operator running low-cost, long-distance electric services on the East Coast Main Line between London and northeastern England.
  • B. Luma
    Luma is a small, star-shaped celestial creature from the Super Mario series, known for its cute appearance and connection to Rosalina and the cosmos.
  • C. Luz
    Luz was the nickname of Carl Ludwig Long, a German long jumper best known for his sportsmanship toward Jesse Owens at the 1936 Berlin Olympics.
  • D. Luz
    Luz is a major railway and metro hub in São Paulo, Brazil, serving as a key interchange point for multiple urban transit lines.
  • E. Luz
    Luz is a small coastal settlement on Graciosa Island in Portugal’s Azores archipelago.
  • 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: Lumas
Triple: [Comet Observatory, primaryResident, Lumas]
Generated description
Lumas are small, star-like creatures in the Super Mario Galaxy series who accompany Rosalina and help power the Comet Observatory.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lumas
Target entity description: Lumas are small, star-like creatures in the Super Mario Galaxy series who accompany Rosalina and help power the Comet Observatory.
  • A. Lumo
    Lumo is a British open-access train operator running low-cost, long-distance electric services on the East Coast Main Line between London and northeastern England.
  • B. Luma chosen
    Luma is a small, star-shaped celestial creature from the Super Mario series, known for its cute appearance and connection to Rosalina and the cosmos.
  • C. Luz
    Luz was the nickname of Carl Ludwig Long, a German long jumper best known for his sportsmanship toward Jesse Owens at the 1936 Berlin Olympics.
  • D. Luz
    Luz is a major railway and metro hub in São Paulo, Brazil, serving as a key interchange point for multiple urban transit lines.
  • E. Luz
    Luz is a small coastal settlement on Graciosa Island in Portugal’s Azores archipelago.
  • F. None of above.

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_69d85cc521a08190921fb50319dddc34 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e0442e327c8190b4b879c8a3cd38e3 completed April 16, 2026, 2:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff4c39ffbc819089cea285e8145fa4 completed May 9, 2026, 3:01 p.m.
NEDg Description generation batch_69ff4ccbd1048190b7f40ede90da7640 completed May 9, 2026, 3:03 p.m.
NED2 Entity disambiguation (via description) batch_69ff4d4033348190a209029d3d2f207b completed May 9, 2026, 3:05 p.m.
Created at: April 10, 2026, 4:06 a.m.