Triple

T8854335
Position Surface form Disambiguated ID Type / Status
Subject Museum aan de Stroom E210714 entity
Predicate shortName P43 FINISHED
Object MAS
MAS is a major contemporary museum in Antwerp, Belgium, known for its striking architecture and exhibitions on the city’s history, art, and global connections.
 E762013 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: MAS | Statement: [Museum aan de Stroom, shortName, MAS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MAS
Context triple: [Museum aan de Stroom, shortName, MAS]
  • A. MAS
    MAS is the ICAO airline designator used to identify Malaysia Airlines in international aviation operations.
  • B. MAS
    MAS (Monetary Authority of Singapore) is Singapore’s central bank and integrated financial regulator, responsible for monetary policy, financial supervision, and the stability of the country’s financial system.
  • C. MAS
    MAS is the official Indian Railways station code for Chennai Central, one of the busiest and most important railway terminals in South India.
  • D. MAS
    MAS is a sports club based in Saint-Étienne, France, known for its participation in regional football competitions.
  • E. MASI
    MASI is the main all-share stock market index of the Casablanca Stock Exchange in Morocco, tracking the performance of its listed companies.
  • 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: MAS
Triple: [Museum aan de Stroom, shortName, MAS]
Generated description
MAS is a major contemporary museum in Antwerp, Belgium, known for its striking architecture and exhibitions on the city’s history, art, and global connections.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MAS
Target entity description: MAS is a major contemporary museum in Antwerp, Belgium, known for its striking architecture and exhibitions on the city’s history, art, and global connections.
  • A. MAS
    MAS is the ICAO airline designator used to identify Malaysia Airlines in international aviation operations.
  • B. MAS
    MAS (Monetary Authority of Singapore) is Singapore’s central bank and integrated financial regulator, responsible for monetary policy, financial supervision, and the stability of the country’s financial system.
  • C. MAS
    MAS is the official Indian Railways station code for Chennai Central, one of the busiest and most important railway terminals in South India.
  • D. MAS
    MAS is a sports club based in Saint-Étienne, France, known for its participation in regional football competitions.
  • E. MASI
    MASI is the main all-share stock market index of the Casablanca Stock Exchange in Morocco, tracking the performance of its listed companies.
  • 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_69ca838a424c8190b1ecac115c2927e7 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc60c6dce88190b175698b191fb89b completed April 1, 2026, 12:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfa09557dc81908b5690bf5c392528 completed April 3, 2026, 11:12 a.m.
NEDg Description generation batch_69cfa1503654819086db66f237f035a1 completed April 3, 2026, 11:15 a.m.
NED2 Entity disambiguation (via description) batch_69cfa1b051cc8190b95c930883cec519 completed April 3, 2026, 11:17 a.m.
Created at: March 30, 2026, 6:49 p.m.