Triple

T5749724
Position Surface form Disambiguated ID Type / Status
Subject Antwerp Province E126820 entity
Predicate contains P35 FINISHED
Object Mol
Mol is a municipality in the Belgian region of Flanders known for its lakes, nature reserves, and recreational tourism.
 E543566 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: Mol | Statement: [Antwerp Province, contains, Mol]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mol
Context triple: [Antwerp Province, contains, Mol]
  • A. MOF
    MOF is the commonly used abbreviation for Japan’s Ministry of Finance, the government body responsible for national fiscal and economic policy.
  • B. Milorg
    Milorg was the main Norwegian military resistance organization during World War II, coordinating sabotage, intelligence, and preparations for liberation under German occupation.
  • C. MSO
    MSO is the National Rail station code for Moston railway station in Greater Manchester, England.
  • D. Molten
    Molten is a Japanese sports equipment manufacturer best known for producing high-quality balls used in major international competitions across football, basketball, and other sports.
  • E. Fremulon
    Fremulon is a television production company founded by Michael Schur, best known for producing acclaimed comedy series such as Brooklyn Nine-Nine.
  • 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: Mol
Triple: [Antwerp Province, contains, Mol]
Generated description
Mol is a municipality in the Belgian region of Flanders known for its lakes, nature reserves, and recreational tourism.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mol
Target entity description: Mol is a municipality in the Belgian region of Flanders known for its lakes, nature reserves, and recreational tourism.
  • A. MOF
    MOF is the commonly used abbreviation for Japan’s Ministry of Finance, the government body responsible for national fiscal and economic policy.
  • B. Milorg
    Milorg was the main Norwegian military resistance organization during World War II, coordinating sabotage, intelligence, and preparations for liberation under German occupation.
  • C. MSO
    MSO is the National Rail station code for Moston railway station in Greater Manchester, England.
  • D. Molten
    Molten is a Japanese sports equipment manufacturer best known for producing high-quality balls used in major international competitions across football, basketball, and other sports.
  • E. Fremulon
    Fremulon is a television production company founded by Michael Schur, best known for producing acclaimed comedy series such as Brooklyn Nine-Nine.
  • 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_69c00832aedc81909899801b141fa3b4 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0288870fc819080e883c9d589359b completed March 22, 2026, 5:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69c07e358d908190a37e5df89df3aedc completed March 22, 2026, 11:41 p.m.
NEDg Description generation batch_69c089020764819090a1927c65f9e870 completed March 23, 2026, 12:27 a.m.
NED2 Entity disambiguation (via description) batch_69c0897b75e481909adc413fa73e9496 completed March 23, 2026, 12:29 a.m.
Created at: March 22, 2026, 3:48 p.m.