Triple

T14747744
Position Surface form Disambiguated ID Type / Status
Subject Belgian Federal Public Service Science Policy E346517 entity
Predicate shortName P43 FINISHED
Object BELSPO
BELSPO is the Belgian federal government body responsible for developing and implementing national science policy and coordinating research programs and scientific institutions.
E1117987 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: BELSPO | Statement: [Belgian Federal Public Service Science Policy, shortName, BELSPO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BELSPO
Context triple: [Belgian Federal Public Service Science Policy, shortName, BELSPO]
  • A. De Bolle
    De Bolle is the surname of Catherine De Bolle, a prominent Belgian police official and former Executive Director of Europol.
  • B. Bollen
    Bollen is a village that forms part of the municipality of Achim in Lower Saxony, Germany.
  • C. Borsele
    Borsele is a municipality in the Dutch province of Zeeland, known for its rural landscape, villages, and the nearby Borssele nuclear power plant.
  • D. Bruls
    Bruls is a Dutch surname most notably borne by Hubert Bruls, a Dutch politician and long-serving mayor of Nijmegen.
  • E. BORL
    BORL was the stock ticker symbol for Borland, a software company known for its development tools and programming environments such as Turbo Pascal and Delphi.
  • 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: BELSPO
Triple: [Belgian Federal Public Service Science Policy, shortName, BELSPO]
Generated description
BELSPO is the Belgian federal government body responsible for developing and implementing national science policy and coordinating research programs and scientific institutions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: BELSPO
Target entity description: BELSPO is the Belgian federal government body responsible for developing and implementing national science policy and coordinating research programs and scientific institutions.
  • A. De Bolle
    De Bolle is the surname of Catherine De Bolle, a prominent Belgian police official and former Executive Director of Europol.
  • B. Bollen
    Bollen is a village that forms part of the municipality of Achim in Lower Saxony, Germany.
  • C. Borsele
    Borsele is a municipality in the Dutch province of Zeeland, known for its rural landscape, villages, and the nearby Borssele nuclear power plant.
  • D. Bruls
    Bruls is a Dutch surname most notably borne by Hubert Bruls, a Dutch politician and long-serving mayor of Nijmegen.
  • E. BORL
    BORL was the stock ticker symbol for Borland, a software company known for its development tools and programming environments such as Turbo Pascal and Delphi.
  • 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_69d822e6f1c88190bc494d491a907114 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec7d116e88190828b163b18d80f68 completed April 14, 2026, 11:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdfb982b5c8190a0340be2186f8b81 completed May 8, 2026, 3:04 p.m.
NEDg Description generation batch_69fdfea2b720819089110c02dbd848bd completed May 8, 2026, 3:17 p.m.
NED2 Entity disambiguation (via description) batch_69fdff1368e48190bc079645996d85d8 completed May 8, 2026, 3:19 p.m.
Created at: April 10, 2026, 1:30 a.m.