Triple

T15550836
Position Surface form Disambiguated ID Type / Status
Subject Tramway T13 Express E370737 entity
Predicate serves P98 FINISHED
Object Mareil-Marly
Mareil-Marly is a small suburban commune in the Yvelines department of north-central France, located west of Paris.
E1163265 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: Mareil-Marly | Statement: [Tramway T13 Express, serves, Mareil-Marly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mareil-Marly
Context triple: [Tramway T13 Express, serves, Mareil-Marly]
  • A. Bonnes-Mares
    Bonnes-Mares is a prestigious Grand Cru vineyard in Burgundy’s Côte de Nuits, renowned for producing powerful, long-lived red wines primarily from Pinot Noir.
  • B. Jaunay-Marigny
    Jaunay-Marigny is a commune in western France’s Vienne department, notable for hosting the popular Futuroscope theme park.
  • C. Marloie
    Marloie is a village in the Walloon region of Belgium known for its railway station on the Brussels–Luxembourg line.
  • D. Marsannay
    Marsannay is a Burgundy wine appellation at the northern end of the Côte de Nuits, known for producing red, white, and rosé wines.
  • E. Maurepas
    Maurepas is a commune in the Yvelines department in the Île-de-France region of north-central France, known as a residential suburb southwest of Paris.
  • 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: Mareil-Marly
Triple: [Tramway T13 Express, serves, Mareil-Marly]
Generated description
Mareil-Marly is a small suburban commune in the Yvelines department of north-central France, located west of Paris.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mareil-Marly
Target entity description: Mareil-Marly is a small suburban commune in the Yvelines department of north-central France, located west of Paris.
  • A. Bonnes-Mares
    Bonnes-Mares is a prestigious Grand Cru vineyard in Burgundy’s Côte de Nuits, renowned for producing powerful, long-lived red wines primarily from Pinot Noir.
  • B. Jaunay-Marigny
    Jaunay-Marigny is a commune in western France’s Vienne department, notable for hosting the popular Futuroscope theme park.
  • C. Marloie
    Marloie is a village in the Walloon region of Belgium known for its railway station on the Brussels–Luxembourg line.
  • D. Marsannay
    Marsannay is a Burgundy wine appellation at the northern end of the Côte de Nuits, known for producing red, white, and rosé wines.
  • E. Maurepas
    Maurepas is a commune in the Yvelines department in the Île-de-France region of north-central France, known as a residential suburb southwest of Paris.
  • 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_69d85cc6cf40819091f4a5facee1ebe6 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04a9551288190a583e8291c35f521 completed April 16, 2026, 2:33 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff455dfbcc8190a93e90c59b2d3045 completed May 9, 2026, 2:31 p.m.
NEDg Description generation batch_69ff467e5d6c8190ba3bf6557e683233 completed May 9, 2026, 2:36 p.m.
NED2 Entity disambiguation (via description) batch_69ff470912bc8190a42ee312aca55872 completed May 9, 2026, 2:39 p.m.
Created at: April 10, 2026, 4:08 a.m.