Triple

T7268355
Position Surface form Disambiguated ID Type / Status
Subject Gherdëina E161035 entity
Predicate closelyRelatedTo P37 FINISHED
Object Fodom Ladin
Fodom Ladin is the variety of the Ladin language traditionally spoken in the Fodom (Livinallongo) valley of the Dolomites in northern Italy.
E652913 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: Fodom Ladin | Statement: [Gherdëina, closelyRelatedTo, Fodom Ladin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fodom Ladin
Context triple: [Gherdëina, closelyRelatedTo, Fodom Ladin]
  • A. Dommoc
    Dommoc was an early medieval ecclesiastical and likely political center of the Anglo-Saxon Kingdom of the East Angles, traditionally identified with a site on the Suffolk coast in England.
  • B. Folmar
    Folmar is a masculine given name of Scandinavian origin, most notably borne by the Danish-American film editor Folmar Blangsted.
  • C. Dragomir
    Dragomir is a Swedish actor and former criminal best known internationally for his role in the film "Easy Money" and appearances in action movies and TV series.
  • D. Loferl
    Loferl are traditional Bavarian calf-warmers or split socks typically worn with Lederhosen as part of Alpine folk costume.
  • E. Fadal
    Fadal is the surname of American actress and model Shannon Elizabeth, known for her roles in films like "American Pie" and "Scary Movie."
  • 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: Fodom Ladin
Triple: [Gherdëina, closelyRelatedTo, Fodom Ladin]
Generated description
Fodom Ladin is the variety of the Ladin language traditionally spoken in the Fodom (Livinallongo) valley of the Dolomites in northern Italy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Fodom Ladin
Target entity description: Fodom Ladin is the variety of the Ladin language traditionally spoken in the Fodom (Livinallongo) valley of the Dolomites in northern Italy.
  • A. Dommoc
    Dommoc was an early medieval ecclesiastical and likely political center of the Anglo-Saxon Kingdom of the East Angles, traditionally identified with a site on the Suffolk coast in England.
  • B. Folmar
    Folmar is a masculine given name of Scandinavian origin, most notably borne by the Danish-American film editor Folmar Blangsted.
  • C. Dragomir
    Dragomir is a Swedish actor and former criminal best known internationally for his role in the film "Easy Money" and appearances in action movies and TV series.
  • D. Loferl
    Loferl are traditional Bavarian calf-warmers or split socks typically worn with Lederhosen as part of Alpine folk costume.
  • E. Fadal
    Fadal is the surname of American actress and model Shannon Elizabeth, known for her roles in films like "American Pie" and "Scary Movie."
  • 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_69c6885181008190b419040e22939c7c completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6eae8cc288190bc3ae3c7b38980d0 completed March 27, 2026, 8:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7db1e4f9c8190a23ce5a35073b7c7 completed March 28, 2026, 1:43 p.m.
NEDg Description generation batch_69c7dbd350a08190aa34ada9ba8d39ce completed March 28, 2026, 1:46 p.m.
NED2 Entity disambiguation (via description) batch_69c7dc7cb2d48190a40523eb7b03a9ef completed March 28, 2026, 1:49 p.m.
Created at: March 27, 2026, 2:58 p.m.