Triple

T3498167
Position Surface form Disambiguated ID Type / Status
Subject Alpes-Maritimes E73900 entity
Predicate containsCity P294 FINISHED
Object Levens
Levens is a small commune in southeastern France situated in the Alpes-Maritimes department of the Provence-Alpes-Côte d'Azur region.
 E362742 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: Levens | Statement: [Alpes-Maritimes, containsCity, Levens]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Levens
Context triple: [Alpes-Maritimes, containsCity, Levens]
  • A. Levens
    Levens is a village in Cumbria, England, known for its rural setting near the River Kent and the historic Levens Hall estate.
  • B. Leven
    Leven is a coastal town in eastern Scotland, situated on the Firth of Forth in the council area of Fife.
  • C. Wilrijk
    Wilrijk is a southern district of the Belgian city of Antwerp, known for its residential character and green spaces.
  • D. Landsmeer
    Landsmeer is a small Dutch town and municipality in North Holland, situated just north of Amsterdam and known for its watery landscapes and nature reserves.
  • E. Heezen
    Heezen is a surname most notably associated with American geologist and oceanographer Bruce C. Heezen, a pioneer in mapping the ocean floor.
  • 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: Levens
Triple: [Alpes-Maritimes, containsCity, Levens]
Generated description
Levens is a small commune in southeastern France situated in the Alpes-Maritimes department of the Provence-Alpes-Côte d'Azur region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Levens
Target entity description: Levens is a small commune in southeastern France situated in the Alpes-Maritimes department of the Provence-Alpes-Côte d'Azur region.
  • A. Levens
    Levens is a village in Cumbria, England, known for its rural setting near the River Kent and the historic Levens Hall estate.
  • B. Leven
    Leven is a coastal town in eastern Scotland, situated on the Firth of Forth in the council area of Fife.
  • C. Wilrijk
    Wilrijk is a southern district of the Belgian city of Antwerp, known for its residential character and green spaces.
  • D. Landsmeer
    Landsmeer is a small Dutch town and municipality in North Holland, situated just north of Amsterdam and known for its watery landscapes and nature reserves.
  • E. Heezen
    Heezen is a surname most notably associated with American geologist and oceanographer Bruce C. Heezen, a pioneer in mapping the ocean floor.
  • 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_69ad85cdb6e48190a335d412b9194ed8 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adbbd299ec8190b76b165b2fd70537 completed March 8, 2026, 6:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69b373d011c0819088245afe03be3c44 completed March 13, 2026, 2:17 a.m.
NEDg Description generation batch_69b3745c7304819085a47af79cd738c0 completed March 13, 2026, 2:20 a.m.
NED2 Entity disambiguation (via description) batch_69b374f5999c8190ae48570a412dc6dc completed March 13, 2026, 2:22 a.m.
Created at: March 8, 2026, 3:18 p.m.