Triple

T16777658
Position Surface form Disambiguated ID Type / Status
Subject Hochschule RheinMain E407768 entity
Predicate hasAbbreviation P43 FINISHED
Object HSRM
HSRM is the abbreviation for Hochschule RheinMain, a university of applied sciences based in the Rhine-Main region of Germany offering a range of practice-oriented academic programs.
 E1233496 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: HSRM | Statement: [Hochschule RheinMain, hasAbbreviation, HSRM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HSRM
Context triple: [Hochschule RheinMain, hasAbbreviation, HSRM]
  • A. HRM
    HRM is the acronym commonly used for the Croatian Navy, the maritime branch of Croatia’s armed forces.
  • B. HRM
    HRM is a common abbreviation for the Halifax Regional Municipality, the local government area encompassing the city of Halifax and surrounding communities in Nova Scotia, Canada.
  • C. HR
    HR is the official vehicle registration code used on license plates for motor vehicles registered in the Indian state of Haryana.
  • D. HR
    HR is the two-letter ISO 3166 country code representing the Republic of Croatia.
  • E. HRMS
    HRMS is the commonly used abbreviation for Holly Ridge Middle School, an educational institution serving middle-grade students.
  • 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: HSRM
Triple: [Hochschule RheinMain, hasAbbreviation, HSRM]
Generated description
HSRM is the abbreviation for Hochschule RheinMain, a university of applied sciences based in the Rhine-Main region of Germany offering a range of practice-oriented academic programs.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HSRM
Target entity description: HSRM is the abbreviation for Hochschule RheinMain, a university of applied sciences based in the Rhine-Main region of Germany offering a range of practice-oriented academic programs.
  • A. HRM
    HRM is the acronym commonly used for the Croatian Navy, the maritime branch of Croatia’s armed forces.
  • B. HRM
    HRM is a common abbreviation for the Halifax Regional Municipality, the local government area encompassing the city of Halifax and surrounding communities in Nova Scotia, Canada.
  • C. HR
    HR is the official vehicle registration code used on license plates for motor vehicles registered in the Indian state of Haryana.
  • D. HR
    HR is the two-letter ISO 3166 country code representing the Republic of Croatia.
  • E. HRMS
    HRMS is the commonly used abbreviation for Holly Ridge Middle School, an educational institution serving middle-grade students.
  • 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_69d8839270588190886720d9519bbf8f completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b212fc248190a8fe1124853bf16d completed April 18, 2026, 4:32 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00aafe1f8081909b9540aca6e7b9b7 completed May 10, 2026, 3:57 p.m.
NEDg Description generation batch_6a00ac0e10648190803bf962a4677104 completed May 10, 2026, 4:02 p.m.
NED2 Entity disambiguation (via description) batch_6a00acc3a9dc819087e07e539760bf34 completed May 10, 2026, 4:05 p.m.
Created at: April 10, 2026, 5:22 a.m.