Triple

T15323476
Position Surface form Disambiguated ID Type / Status
Subject Autoriteit Consument en Markt E366352 entity
Predicate shortName P43 FINISHED
Object ACM
ACM is the Dutch Authority for Consumers and Markets, an independent regulator overseeing competition, consumer protection, and key network sectors in the Netherlands.
 E1150168 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: ACM | Statement: [Autoriteit Consument en Markt, shortName, ACM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ACM
Context triple: [Autoriteit Consument en Markt, shortName, ACM]
  • A. ACM
    ACM is a leading international scientific and educational computing society known for publishing research journals, organizing conferences, and advancing the field of computer science.
  • B. ACM
    ACM is the stock ticker symbol for AECOM, a global infrastructure consulting and engineering firm.
  • C. ACM
    ACM is the commonly used abbreviation for the Appellate Court of Maryland, an intermediate appellate court in the Maryland state judiciary.
  • D. ACM
    ACM is an abbreviation commonly used to refer to Alarm Communication Management, a system or framework for handling and coordinating alarm-related communications.
  • E. ACM
    ACM is a senior four-star air officer rank used in several air forces, typically held by the professional head of the service.
  • 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: ACM
Triple: [Autoriteit Consument en Markt, shortName, ACM]
Generated description
ACM is the Dutch Authority for Consumers and Markets, an independent regulator overseeing competition, consumer protection, and key network sectors in the Netherlands.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ACM
Target entity description: ACM is the Dutch Authority for Consumers and Markets, an independent regulator overseeing competition, consumer protection, and key network sectors in the Netherlands.
  • A. ACM
    ACM is the commonly used abbreviation for the Appellate Court of Maryland, an intermediate appellate court in the Maryland state judiciary.
  • B. ACM
    ACM is an abbreviation commonly used to refer to Alarm Communication Management, a system or framework for handling and coordinating alarm-related communications.
  • C. ACM
    ACM is a senior four-star air officer rank used in several air forces, typically held by the professional head of the service.
  • D. ACM
    ACM is a leading international scientific and educational computing society known for publishing research journals, organizing conferences, and advancing the field of computer science.
  • E. ACM
    ACM is the stock ticker symbol for AECOM, a global infrastructure consulting and engineering firm.
  • 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_69d85a121520819093dcce999fdefe1a completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03dd5ce0c819093c9a14de549dff6 completed April 16, 2026, 1:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69fef8aaef608190bd3ec9fdd215afbb completed May 9, 2026, 9:04 a.m.
NEDg Description generation batch_69fefa435efc81908c1e88267e745cdd completed May 9, 2026, 9:11 a.m.
NED2 Entity disambiguation (via description) batch_69fefb2ee9108190b3d8633cc9713c7b completed May 9, 2026, 9:15 a.m.
Created at: April 10, 2026, 3:16 a.m.