Triple

T20976735
Position Surface form Disambiguated ID Type / Status
Subject Cluse de Pontarlier E516645 entity
Predicate geologicalType P940 FINISHED
Object cluse
A cluse is a narrow transverse valley or gorge cut by a river through a mountain ridge or anticline, often forming a striking natural passage.
E1460315 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: cluse | Statement: [Cluse de Pontarlier, geologicalType, cluse]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: cluse
Context triple: [Cluse de Pontarlier, geologicalType, cluse]
  • A. Clus
    Clus is a historical name for the city of Kolozsvár (modern-day Cluj-Napoca) in Transylvania, Romania.
  • B. CLU
    CLU is an early high-level programming language from the 1970s that pioneered data abstraction, iterators, and exception handling, significantly influencing the design of later languages.
  • C. CLU
    CLU is a private liberal arts university in Thousand Oaks, California, known for its programs in business, education, and the humanities within a Lutheran tradition.
  • D. LUCL
    LUCL is a research and teaching institute at Leiden University specializing in linguistics and language-related studies.
  • E. CLE
    CLE is the standard abbreviation used for the Cleveland Monsters, a professional ice hockey team in the American Hockey League.
  • 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: cluse
Triple: [Cluse de Pontarlier, geologicalType, cluse]
Generated description
A cluse is a narrow transverse valley or gorge cut by a river through a mountain ridge or anticline, often forming a striking natural passage.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: cluse
Target entity description: A cluse is a narrow transverse valley or gorge cut by a river through a mountain ridge or anticline, often forming a striking natural passage.
  • A. Clus
    Clus is a historical name for the city of Kolozsvár (modern-day Cluj-Napoca) in Transylvania, Romania.
  • B. CLU
    CLU is an early high-level programming language from the 1970s that pioneered data abstraction, iterators, and exception handling, significantly influencing the design of later languages.
  • C. CLU
    CLU is a private liberal arts university in Thousand Oaks, California, known for its programs in business, education, and the humanities within a Lutheran tradition.
  • D. LUCL
    LUCL is a research and teaching institute at Leiden University specializing in linguistics and language-related studies.
  • E. CLE
    CLE is the standard abbreviation used for the Cleveland Monsters, a professional ice hockey team in the American Hockey League.
  • 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_69e0b4fee5ac8190875fa9ceba1a5e5e completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fba4a0dc819083b90795d26adfff completed April 21, 2026, 4:23 a.m.
NED1 Entity disambiguation (via context triple) batch_6a092fbec34c819090f2a503633b7d3b completed May 17, 2026, 3:02 a.m.
NEDg Description generation batch_6a093063be9c8190869f4e680aa7bff5 completed May 17, 2026, 3:05 a.m.
NED2 Entity disambiguation (via description) batch_6a0930c7e674819087c0c53cfdd1697f completed May 17, 2026, 3:06 a.m.
Created at: April 16, 2026, 1:47 p.m.