Triple

T15928474
Position Surface form Disambiguated ID Type / Status
Subject Lyon tram line T2 E386264 entity
Predicate terminus P388 FINISHED
Object Saint-Priest Bel-Air
Saint-Priest Bel-Air is a tram terminus located in the eastern suburbs of Lyon, France, serving the commune of Saint-Priest.
E1184904 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: Saint-Priest Bel-Air | Statement: [Lyon tram line T2, terminus, Saint-Priest Bel-Air]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saint-Priest Bel-Air
Context triple: [Lyon tram line T2, terminus, Saint-Priest Bel-Air]
  • A. Ville Parle
    Ville Parle is a prominent suburban neighborhood in Mumbai, India, known for its residential areas, educational institutions, and proximity to the city’s western coastline.
  • B. Delmas
    Delmas is a town in South Africa’s Mpumalanga province known for its agriculture and coal mining activities.
  • C. Delmas
    Delmas is a densely populated suburban commune forming part of the Port-au-Prince metropolitan area in Haiti.
  • D. Rawsonville
    Rawsonville is a small wine-producing town in South Africa’s Western Cape, known for its vineyards, cellars, and scenic Breede River Valley setting.
  • E. Parlier
    Parlier is a small agricultural city in California’s San Joaquin Valley, known for its large farmworker community and fruit production.
  • 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: Saint-Priest Bel-Air
Triple: [Lyon tram line T2, terminus, Saint-Priest Bel-Air]
Generated description
Saint-Priest Bel-Air is a tram terminus located in the eastern suburbs of Lyon, France, serving the commune of Saint-Priest.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Saint-Priest Bel-Air
Target entity description: Saint-Priest Bel-Air is a tram terminus located in the eastern suburbs of Lyon, France, serving the commune of Saint-Priest.
  • A. Ville Parle
    Ville Parle is a prominent suburban neighborhood in Mumbai, India, known for its residential areas, educational institutions, and proximity to the city’s western coastline.
  • B. Delmas
    Delmas is a densely populated suburban commune forming part of the Port-au-Prince metropolitan area in Haiti.
  • C. Delmas
    Delmas is a town in South Africa’s Mpumalanga province known for its agriculture and coal mining activities.
  • D. Rawsonville
    Rawsonville is a small wine-producing town in South Africa’s Western Cape, known for its vineyards, cellars, and scenic Breede River Valley setting.
  • E. Parlier
    Parlier is a small agricultural city in California’s San Joaquin Valley, known for its large farmworker community and fruit production.
  • 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_69d86da750008190987eb26be3f6c118 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156a39abc8190927818f6e185033a completed April 16, 2026, 9:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb5b0833081909668c042234b5b75 completed May 9, 2026, 10:31 p.m.
NEDg Description generation batch_69ffb6a526188190be80658fb23cacbd completed May 9, 2026, 10:35 p.m.
NED2 Entity disambiguation (via description) batch_69ffb71cea948190a1c5998654aee8d5 completed May 9, 2026, 10:37 p.m.
Created at: April 10, 2026, 4:52 a.m.