Triple

T1893357
Position Surface form Disambiguated ID Type / Status
Subject NVIDIA Omniverse E41921 entity
Predicate usesFileFormat P8463 FINISHED
Object MDL
MDL (Material Definition Language) is NVIDIA’s high-level language for defining physically based materials and their appearance consistently across different rendering and simulation platforms.
 E209954 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: MDL | Statement: [NVIDIA Omniverse, usesFileFormat, MDL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MDL
Context triple: [NVIDIA Omniverse, usesFileFormat, MDL]
  • A. MDL
    MDL is the abbreviation commonly used for the Military Demarcation Line that separates North and South Korea along the Korean Demilitarized Zone.
  • B. MDL
    MDL is the official currency code for the Moldovan leu, the national currency of Moldova.
  • C. MDE
    MDE is the state agency in Maryland responsible for protecting and restoring the environment and public health through regulation, monitoring, and enforcement of environmental laws.
  • D. MDT
    MDT is the stock ticker symbol for Medtronic, a leading global medical technology company specializing in devices and therapies for chronic diseases.
  • E. MDU
    MDU is the official county code used to identify Madera County in administrative and governmental contexts.
  • 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: MDL
Triple: [NVIDIA Omniverse, usesFileFormat, MDL]
Generated description
MDL (Material Definition Language) is NVIDIA’s high-level language for defining physically based materials and their appearance consistently across different rendering and simulation platforms.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MDL
Target entity description: MDL (Material Definition Language) is NVIDIA’s high-level language for defining physically based materials and their appearance consistently across different rendering and simulation platforms.
  • A. MDL
    MDL is the abbreviation commonly used for the Military Demarcation Line that separates North and South Korea along the Korean Demilitarized Zone.
  • B. MDL
    MDL is the official currency code for the Moldovan leu, the national currency of Moldova.
  • C. MDE
    MDE is the state agency in Maryland responsible for protecting and restoring the environment and public health through regulation, monitoring, and enforcement of environmental laws.
  • D. MDT
    MDT is the stock ticker symbol for Medtronic, a leading global medical technology company specializing in devices and therapies for chronic diseases.
  • E. MDU
    MDU is the official county code used to identify Madera County in administrative and governmental contexts.
  • 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_69a8864b6de0819098d089f6a1b910a7 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb7c376208190bbf28504f1aac881 completed March 7, 2026, 5:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69addf6aba788190bb30420375b5db7f completed March 8, 2026, 8:43 p.m.
NEDg Description generation batch_69addfe604708190b85d6f7261197537 completed March 8, 2026, 8:45 p.m.
NED2 Entity disambiguation (via description) batch_69ade0919d748190a4326d4abca2c9eb completed March 8, 2026, 8:48 p.m.
Created at: March 4, 2026, 7:34 p.m.