Triple

T19633406
Position Surface form Disambiguated ID Type / Status
Subject Anacostia Freeway (I-295) E471327 entity
Predicate connectsTo P845 FINISHED
Object DC-295
DC-295 is a major freeway in Washington, D.C. that serves as a key north–south commuter and regional traffic corridor.
 E1386335 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: DC-295 | Statement: [Anacostia Freeway (I-295), connectsTo, DC-295]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: DC-295
Context triple: [Anacostia Freeway (I-295), connectsTo, DC-295]
  • A. D290
    D290 is a designated regional road identified by the route number D290 within a national road network.
  • B. DC35
    DC35 is the official municipal code designating the Capricorn District Municipality in South Africa’s Limpopo province.
  • C. C-29
    The C-29 is a U.S. military variant of the British Hawker Siddeley HS 125 business jet used primarily for transport and training roles.
  • D. D-2500
    D-2500 was the German civil-registered prototype and primary example of the Junkers G 38, a large all-metal four-engine transport aircraft of the late 1920s and early 1930s.
  • E. C-95
    C-95 is the Brazilian Air Force’s military transport and utility aircraft designation for the Embraer EMB-110 Bandeirante.
  • 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: DC-295
Triple: [Anacostia Freeway (I-295), connectsTo, DC-295]
Generated description
DC-295 is a major freeway in Washington, D.C. that serves as a key north–south commuter and regional traffic corridor.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: DC-295
Target entity description: DC-295 is a major freeway in Washington, D.C. that serves as a key north–south commuter and regional traffic corridor.
  • A. D290
    D290 is a designated regional road identified by the route number D290 within a national road network.
  • B. DC35
    DC35 is the official municipal code designating the Capricorn District Municipality in South Africa’s Limpopo province.
  • C. C-29
    The C-29 is a U.S. military variant of the British Hawker Siddeley HS 125 business jet used primarily for transport and training roles.
  • D. D-2500
    D-2500 was the German civil-registered prototype and primary example of the Junkers G 38, a large all-metal four-engine transport aircraft of the late 1920s and early 1930s.
  • E. C-95
    C-95 is the Brazilian Air Force’s military transport and utility aircraft designation for the Embraer EMB-110 Bandeirante.
  • 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_69d8e511f28481909f4bc3ea9191e54a completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e6410449ec8190b8c20c0e09cd9156 completed April 20, 2026, 3:06 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0771c3fb608190ac10cb35014f1b5a completed May 15, 2026, 7:19 p.m.
NEDg Description generation batch_6a07731b33f88190b34aa3f29ca530e9 completed May 15, 2026, 7:25 p.m.
NED2 Entity disambiguation (via description) batch_6a0773de9e90819081e45eb66ccdfcee completed May 15, 2026, 7:28 p.m.
Created at: April 10, 2026, 1:44 p.m.