Triple

T19085837
Position Surface form Disambiguated ID Type / Status
Subject BR-163 highway E467146 entity
Predicate maintainedBy P86 FINISHED
Object DNIT
DNIT is Brazil’s federal National Department of Transport Infrastructure, responsible for managing and maintaining the country’s federal highways and related transport works.
 E1357132 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: DNIT | Statement: [BR-163 highway, maintainedBy, DNIT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: DNIT
Context triple: [BR-163 highway, maintainedBy, DNIT]
  • A. DNIL
    DNIL is the ICAO airport code assigned to Ilorin International Airport in Ilorin, Nigeria.
  • B. NITT
    NITT is a premier public engineering and technology institute in Tiruchirappalli, India, renowned for its rigorous academics and research.
  • C. DN
    DN is the official vehicle registration code used for the Indian union territory of Dadra and Nagar Haveli and Daman and Diu.
  • D. DN
    DN is a UK postcode area covering Doncaster and surrounding parts of South Yorkshire and Lincolnshire, including North East Lincolnshire.
  • E. DN
    DN is the vehicle registration code used on license plates for the district of Düren in the German state of North Rhine-Westphalia.
  • 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: DNIT
Triple: [BR-163 highway, maintainedBy, DNIT]
Generated description
DNIT is Brazil’s federal National Department of Transport Infrastructure, responsible for managing and maintaining the country’s federal highways and related transport works.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: DNIT
Target entity description: DNIT is Brazil’s federal National Department of Transport Infrastructure, responsible for managing and maintaining the country’s federal highways and related transport works.
  • A. DNIL
    DNIL is the ICAO airport code assigned to Ilorin International Airport in Ilorin, Nigeria.
  • B. NITT
    NITT is a premier public engineering and technology institute in Tiruchirappalli, India, renowned for its rigorous academics and research.
  • C. DN
    DN is the official vehicle registration code used for the Indian union territory of Dadra and Nagar Haveli and Daman and Diu.
  • D. DN
    DN is a UK postcode area covering Doncaster and surrounding parts of South Yorkshire and Lincolnshire, including North East Lincolnshire.
  • E. DN
    DN is the vehicle registration code used on license plates for the district of Düren in the German state of North Rhine-Westphalia.
  • 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_69d8dd05ac4c8190b1967d8f97f3fb2f completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e346f57c8190a6299e09a0be9e05 completed April 20, 2026, 8:26 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05d368740c81909ec738532cd670bf completed May 14, 2026, 1:51 p.m.
NEDg Description generation batch_6a05d4ff70d0819089a00de0404768a4 completed May 14, 2026, 1:58 p.m.
NED2 Entity disambiguation (via description) batch_6a05d58227188190928741f15b685cb0 completed May 14, 2026, 2 p.m.
Created at: April 10, 2026, 12:04 p.m.