Triple

T4625265
Position Surface form Disambiguated ID Type / Status
Subject The MAD Museum E101082 entity
Predicate acronym P43 FINISHED
Object MAD
MAD is a museum dedicated to contemporary art and design, showcasing innovative and experimental works across various media.
E456394 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: MAD | Statement: [The MAD Museum, acronym, MAD]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MAD
Context triple: [The MAD Museum, acronym, MAD]
  • A. MAD
    MAD is the three-letter IATA airport code for Adolfo Suárez Madrid–Barajas Airport, the main international airport serving Madrid, Spain.
  • B. U Mad
    "U Mad" is a hip-hop single by American rapper Vic Mensa featuring Kanye West, known for its aggressive energy and confrontational lyrics.
  • C. MDA
    MDA (Monochrome Display Adapter) is IBM's original text-only video display standard for early IBM PCs, providing high-resolution monochrome output without graphics capabilities.
  • D. MDA
    MDA is a Canadian space technology company known for developing advanced satellite systems, robotics, and Earth observation solutions.
  • E. MDA
    MDA is the United States Missile Defense Agency, a Department of Defense organization responsible for developing and deploying systems to defend the U.S. and its allies against ballistic missile threats.
  • 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: MAD
Triple: [The MAD Museum, acronym, MAD]
Generated description
MAD is a museum dedicated to contemporary art and design, showcasing innovative and experimental works across various media.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: MAD
Target entity description: MAD is a museum dedicated to contemporary art and design, showcasing innovative and experimental works across various media.
  • A. MAD
    MAD is the three-letter IATA airport code for Adolfo Suárez Madrid–Barajas Airport, the main international airport serving Madrid, Spain.
  • B. U Mad
    "U Mad" is a hip-hop single by American rapper Vic Mensa featuring Kanye West, known for its aggressive energy and confrontational lyrics.
  • C. MDA
    MDA (Monochrome Display Adapter) is IBM's original text-only video display standard for early IBM PCs, providing high-resolution monochrome output without graphics capabilities.
  • D. MDA
    MDA is a Canadian space technology company known for developing advanced satellite systems, robotics, and Earth observation solutions.
  • E. MDA
    MDA is the United States Missile Defense Agency, a Department of Defense organization responsible for developing and deploying systems to defend the U.S. and its allies against ballistic missile threats.
  • 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_69bd43d0497c8190ac23c65c5804846a completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd5a08ef488190af46418229309b0f completed March 20, 2026, 2:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfaa564988190b565c26b9cd3d3be completed March 21, 2026, 1:55 a.m.
NEDg Description generation batch_69bdfb6fa3fc8190b79b641025710eb1 completed March 21, 2026, 1:59 a.m.
NED2 Entity disambiguation (via description) batch_69bdfbeddd7c8190955bd3363fec4ca1 completed March 21, 2026, 2:01 a.m.
Created at: March 20, 2026, 1:13 p.m.