Triple

T4488301
Position Surface form Disambiguated ID Type / Status
Subject Massachusetts Route 3A E107303 entity
Predicate highwayNumber P1864 FINISHED
Object 3A
3A is a highway designation used for several auxiliary or alternate routes of U.S. Route 3 and related highways in New England.
 E446599 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: 3A | Statement: [Massachusetts Route 3A, highwayNumber, 3A]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: 3A
Context triple: [Massachusetts Route 3A, highwayNumber, 3A]
  • A. A3
    A3 is a major national highway in Zimbabwe that serves as an important route connecting key towns and regions within the country.
  • B. A3
    A3 is a major Swiss motorway that runs across the country’s north, connecting key cities and regions as part of the national highway network.
  • C. A3
    A3 is a major German autobahn that runs across several federal states, serving as an important east–west transport corridor.
  • D. A3
    A3 is the IATA airline designator for Aegean Airlines, the largest Greek airline and a member of the Star Alliance.
  • E. A
    A is a Los Angeles Metro Rail line that runs along the Blue Line corridor, connecting downtown Los Angeles with surrounding communities.
  • 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: 3A
Triple: [Massachusetts Route 3A, highwayNumber, 3A]
Generated description
3A is a highway designation used for several auxiliary or alternate routes of U.S. Route 3 and related highways in New England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: 3A
Target entity description: 3A is a highway designation used for several auxiliary or alternate routes of U.S. Route 3 and related highways in New England.
  • A. A3
    A3 is a major national highway in Zimbabwe that serves as an important route connecting key towns and regions within the country.
  • B. A3
    A3 is the IATA airline designator for Aegean Airlines, the largest Greek airline and a member of the Star Alliance.
  • C. A3
    A3 is a major Swiss motorway that runs across the country’s north, connecting key cities and regions as part of the national highway network.
  • D. A3
    A3 is a major German autobahn that runs across several federal states, serving as an important east–west transport corridor.
  • E. A
    A is a Los Angeles Metro Rail line that runs along the Blue Line corridor, connecting downtown Los Angeles with surrounding communities.
  • 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_69bd43f84f788190a1383579c4a595be completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd52ad36748190b791de458f2116b2 completed March 20, 2026, 1:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69bd67a31d0c819089954c8af4b1bdd6 completed March 20, 2026, 3:28 p.m.
NEDg Description generation batch_69bd69faac508190863892c9bbdb20b3 completed March 20, 2026, 3:38 p.m.
NED2 Entity disambiguation (via description) batch_69bd6a64c64881909acf1171be426fe4 completed March 20, 2026, 3:40 p.m.
Created at: March 20, 2026, 12:59 p.m.