Triple

T13066796
Position Surface form Disambiguated ID Type / Status
Subject Maryland Route 5 E329346 entity
Predicate abbreviation P43 FINISHED
Object MD 5
MD 5 is a primary state highway in Maryland that connects the Washington, D.C. suburbs with Southern Maryland, including the communities of Clinton and Waldorf.
 E1017519 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: MD 5 | Statement: [Maryland Route 5, abbreviation, MD 5]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MD 5
Context triple: [Maryland Route 5, abbreviation, MD 5]
  • A. MD5
    MD5 is a widely known but now cryptographically broken 128-bit hash function formerly used for checksums, data integrity, and security applications.
  • B. MD4
    MD4 is a cryptographic hash function designed by Ronald Rivest that produces a 128-bit hash value and served as the basis for later algorithms like MD5.
  • C. MD 500
    The MD 500 is a family of light, single-engine civilian and military helicopters known for their agility, compact size, and use in roles ranging from transport to law enforcement and special operations.
  • D. MDV
    MDV is a venture capital firm known for investing in early-stage technology and life sciences companies.
  • E. MDV
    MDV is a regional public transport association and fare network serving Leipzig and the surrounding Central German 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: MD 5
Triple: [Maryland Route 5, abbreviation, MD 5]
Generated description
MD 5 is a primary state highway in Maryland that connects the Washington, D.C. suburbs with Southern Maryland, including the communities of Clinton and Waldorf.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MD 5
Target entity description: MD 5 is a primary state highway in Maryland that connects the Washington, D.C. suburbs with Southern Maryland, including the communities of Clinton and Waldorf.
  • A. MD5
    MD5 is a widely known but now cryptographically broken 128-bit hash function formerly used for checksums, data integrity, and security applications.
  • B. MD4
    MD4 is a cryptographic hash function designed by Ronald Rivest that produces a 128-bit hash value and served as the basis for later algorithms like MD5.
  • C. MD 500
    The MD 500 is a family of light, single-engine civilian and military helicopters known for their agility, compact size, and use in roles ranging from transport to law enforcement and special operations.
  • D. MDV
    MDV is a venture capital firm known for investing in early-stage technology and life sciences companies.
  • E. MDV
    MDV is a regional public transport association and fare network serving Leipzig and the surrounding Central German 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_69d80771749c81909a6d9197b9504872 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d980eb81948190b27eb9ae19978079 completed April 10, 2026, 10:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6cbe7abd0819085645e29d43493dd completed May 3, 2026, 4:15 a.m.
NEDg Description generation batch_69f6cd3d5090819091b65f544ad139fd completed May 3, 2026, 4:21 a.m.
NED2 Entity disambiguation (via description) batch_69f6cdc8d52c819083717a455d589646 completed May 3, 2026, 4:23 a.m.
Created at: April 9, 2026, 8:59 p.m.