Triple

T16755968
Position Surface form Disambiguated ID Type / Status
Subject High Council of Justice of Belgium E407205 entity
Predicate hasAbbreviation P43 FINISHED
Object HRJ
HRJ is the abbreviation for Belgium’s High Council of Justice, the independent body overseeing the functioning and integrity of the judiciary.
 E1231376 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: HRJ | Statement: [High Council of Justice of Belgium, hasAbbreviation, HRJ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HRJ
Context triple: [High Council of Justice of Belgium, hasAbbreviation, HRJ]
  • A. HRP
    HRP is a high-level long-distance hiking route that traverses the Pyrenees along or near the French–Spanish border from the Atlantic Ocean to the Mediterranean Sea.
  • B. HRP
    HRP is NASA’s Human Research Program, which investigates and mitigates health and performance risks to enable safe, long-duration human space exploration.
  • C. HRYR
    HRYR is the ICAO airport code for Kigali International Airport, the main international gateway to Rwanda’s capital city.
  • D. RJH
    RJH is the IATA airport code for Shah Makhdum Airport serving Rajshahi in western Bangladesh.
  • E. JR
    JR is the station code assigned to J. Ruiz station in the Manila Metro Rail Transit system.
  • 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: HRJ
Triple: [High Council of Justice of Belgium, hasAbbreviation, HRJ]
Generated description
HRJ is the abbreviation for Belgium’s High Council of Justice, the independent body overseeing the functioning and integrity of the judiciary.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HRJ
Target entity description: HRJ is the abbreviation for Belgium’s High Council of Justice, the independent body overseeing the functioning and integrity of the judiciary.
  • A. HRP
    HRP is a high-level long-distance hiking route that traverses the Pyrenees along or near the French–Spanish border from the Atlantic Ocean to the Mediterranean Sea.
  • B. HRP
    HRP is NASA’s Human Research Program, which investigates and mitigates health and performance risks to enable safe, long-duration human space exploration.
  • C. HRYR
    HRYR is the ICAO airport code for Kigali International Airport, the main international gateway to Rwanda’s capital city.
  • D. RJH
    RJH is the IATA airport code for Shah Makhdum Airport serving Rajshahi in western Bangladesh.
  • E. JR
    JR is a French street artist and photographer renowned for his large-scale public art installations that transform urban spaces and address social and political issues worldwide.
  • 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_69d8839174188190909f190097207065 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3abe831ec8190bac05b07db6153c1 completed April 18, 2026, 4:06 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00a52886e48190b7a1e6fccd9a5709 completed May 10, 2026, 3:32 p.m.
NEDg Description generation batch_6a00a5e1eea8819088553ac6673e9b1c completed May 10, 2026, 3:36 p.m.
NED2 Entity disambiguation (via description) batch_6a00a68b92b48190865ddd477a8ba1c6 completed May 10, 2026, 3:38 p.m.
Created at: April 10, 2026, 5:21 a.m.