Triple

T16901988
Position Surface form Disambiguated ID Type / Status
Subject Judicial Panel on Multidistrict Litigation E424458 entity
Predicate alsoKnownAs P39 FINISHED
Object MDL Panel
The MDL Panel is a specialized federal judicial body that decides whether related civil cases filed in different U.S. districts should be consolidated for coordinated pretrial proceedings.
 E1239591 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 Panel | Statement: [Judicial Panel on Multidistrict Litigation, alsoKnownAs, MDL Panel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MDL Panel
Context triple: [Judicial Panel on Multidistrict Litigation, alsoKnownAs, MDL Panel]
  • A. MDL
    MDL is the official currency code for the Moldovan leu, the national currency of Moldova.
  • B. MDL
    MDL is the abbreviation commonly used for the Military Demarcation Line that separates North and South Korea along the Korean Demilitarized Zone.
  • C. MDL
    MDL is the IATA airport code for Mandalay International Airport, the main air gateway to Mandalay in Myanmar.
  • D. MDL
    MDL is a Lisp-derived programming language developed at MIT for advanced artificial intelligence research and interactive computing.
  • E. 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.
  • 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 Panel
Triple: [Judicial Panel on Multidistrict Litigation, alsoKnownAs, MDL Panel]
Generated description
The MDL Panel is a specialized federal judicial body that decides whether related civil cases filed in different U.S. districts should be consolidated for coordinated pretrial proceedings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MDL Panel
Target entity description: The MDL Panel is a specialized federal judicial body that decides whether related civil cases filed in different U.S. districts should be consolidated for coordinated pretrial proceedings.
  • A. MDL
    MDL is the official currency code for the Moldovan leu, the national currency of Moldova.
  • B. MDL
    MDL is the abbreviation commonly used for the Military Demarcation Line that separates North and South Korea along the Korean Demilitarized Zone.
  • C. MDL
    MDL is the IATA airport code for Mandalay International Airport, the main air gateway to Mandalay in Myanmar.
  • D. MDL
    MDL is a Lisp-derived programming language developed at MIT for advanced artificial intelligence research and interactive computing.
  • E. 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.
  • 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_69d889da3e8c8190a2b118f383f0beac completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e3c8dd2bf08190b1dc099e8a23cd04 completed April 18, 2026, 6:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00c7b273608190b552d8dc22bc51ef completed May 10, 2026, 6 p.m.
NEDg Description generation batch_6a00c88e83b88190919cfa0d10112e53 completed May 10, 2026, 6:03 p.m.
NED2 Entity disambiguation (via description) batch_6a00c90bfeb0819098b93a22d5886c6f completed May 10, 2026, 6:06 p.m.
Created at: April 10, 2026, 5:29 a.m.