Triple

T9934482
Position Surface form Disambiguated ID Type / Status
Subject Federal Public Services of Belgium E192724 entity
Predicate hasComponent P35 FINISHED
Object FPS Employment
FPS Employment is a Belgian federal public service responsible for labor policy, employment regulation, and workplace well-being.
 E831184 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: FPS Employment | Statement: [Federal Public Services of Belgium, hasComponent, FPS Employment]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FPS Employment
Context triple: [Federal Public Services of Belgium, hasComponent, FPS Employment]
  • A. FPS
    FPS is the abbreviation for the Federal Protective Service, a U.S. agency responsible for protecting federal government facilities and their occupants.
  • B. FML
    FML is a moody, introspective Kanye West song from *The Life of Pablo* that explores emotional turmoil, relationships, and mental health over dark, atmospheric production.
  • C. FML
    FML is the National Rail station code for Frimley railway station in Surrey, England.
  • D. FRPS
    FRPS is the highest level of distinction awarded by the Royal Photographic Society, signifying a Fellow recognized for exceptional photographic skill and contribution to the medium.
  • E. FC
    FC is the standard abbreviation for the Federal Court of Canada, a national trial court that hears cases involving federal law.
  • 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: FPS Employment
Triple: [Federal Public Services of Belgium, hasComponent, FPS Employment]
Generated description
FPS Employment is a Belgian federal public service responsible for labor policy, employment regulation, and workplace well-being.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FPS Employment
Target entity description: FPS Employment is a Belgian federal public service responsible for labor policy, employment regulation, and workplace well-being.
  • A. FPS
    FPS is the abbreviation for the Federal Protective Service, a U.S. agency responsible for protecting federal government facilities and their occupants.
  • B. FML
    FML is a moody, introspective Kanye West song from *The Life of Pablo* that explores emotional turmoil, relationships, and mental health over dark, atmospheric production.
  • C. FML
    FML is the National Rail station code for Frimley railway station in Surrey, England.
  • D. FRPS
    FRPS is the highest level of distinction awarded by the Royal Photographic Society, signifying a Fellow recognized for exceptional photographic skill and contribution to the medium.
  • E. FC
    FC is the standard abbreviation for the Federal Court of Canada, a national trial court that hears cases involving federal law.
  • 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_69ca82dd978c8190947124ab0d3315ac completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb5e263208190b6ea8b8b4e29805d completed April 2, 2026, 12:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69d228ddecfc8190850a098bf4074cc3 completed April 5, 2026, 9:18 a.m.
NEDg Description generation batch_69d22cc9284c8190be92710f37877846 completed April 5, 2026, 9:35 a.m.
NED2 Entity disambiguation (via description) batch_69d22d2997ec81909cb1267ab0066cd5 completed April 5, 2026, 9:36 a.m.
Created at: March 30, 2026, 8:44 p.m.