Triple

T12132188
Position Surface form Disambiguated ID Type / Status
Subject Line 2 (Brussels Metro) E288959 entity
Predicate servesStation P839 FINISHED
Object Madou
Madou is a Brussels Metro station on the city's rapid transit network, located near Madou Square in central Brussels.
E963958 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: Madou | Statement: [Line 2 (Brussels Metro), servesStation, Madou]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Madou
Context triple: [Line 2 (Brussels Metro), servesStation, Madou]
  • A. Modau
    The Modau is a small river in the German state of Hesse that flows through the city of Darmstadt before joining the Rhine.
  • B. Midouze
    Midouze is a river in southwestern France that flows through the Landes region before joining the Adour.
  • C. Modogashe
    Modogashe is a small, remote town in northeastern Kenya known as a local trading and transit center in a semi-arid pastoral region.
  • D. Muzna
    Muzna was the mother of Abd al-Rahman III, the powerful 10th-century Umayyad ruler who became the first Caliph of Córdoba in al-Andalus.
  • E. Mudon
    Mudon is a master-planned residential community in Dubai known for its family-friendly environment, townhouses, and extensive amenities.
  • 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: Madou
Triple: [Line 2 (Brussels Metro), servesStation, Madou]
Generated description
Madou is a Brussels Metro station on the city's rapid transit network, located near Madou Square in central Brussels.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Madou
Target entity description: Madou is a Brussels Metro station on the city's rapid transit network, located near Madou Square in central Brussels.
  • A. Modau
    The Modau is a small river in the German state of Hesse that flows through the city of Darmstadt before joining the Rhine.
  • B. Midouze
    Midouze is a river in southwestern France that flows through the Landes region before joining the Adour.
  • C. Modogashe
    Modogashe is a small, remote town in northeastern Kenya known as a local trading and transit center in a semi-arid pastoral region.
  • D. Muzna
    Muzna was the mother of Abd al-Rahman III, the powerful 10th-century Umayyad ruler who became the first Caliph of Córdoba in al-Andalus.
  • E. Mudon
    Mudon is a master-planned residential community in Dubai known for its family-friendly environment, townhouses, and extensive amenities.
  • 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_69d6ab4b5e4c81909950b17151eb0951 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d9158b34648190b5eecdf9b07fbb3f completed April 10, 2026, 3:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69f5f68c8ee081908a0331805f62cb0d completed May 2, 2026, 1:05 p.m.
NEDg Description generation batch_69f5fed2d57881908103ce89a365cdd4 completed May 2, 2026, 1:40 p.m.
NED2 Entity disambiguation (via description) batch_69f600bcaf288190b6204f985d3be638 completed May 2, 2026, 1:48 p.m.
Created at: April 8, 2026, 9:49 p.m.