Triple

T9521992
Position Surface form Disambiguated ID Type / Status
Subject Bavarian Forest National Park E229665 entity
Predicate highestPoint P210 FINISHED
Object Lusen
Lusen is a prominent mountain on the German-Czech border in the Bavarian Forest, known for its rocky summit and extensive hiking trails.
E803883 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: Lusen | Statement: [Bavarian Forest National Park, highestPoint, Lusen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lusen
Context triple: [Bavarian Forest National Park, highestPoint, Lusen]
  • A. Lugensa
    Lugensa is a genus of seabirds in the petrel family Procellariidae, comprising medium-sized, oceanic birds adapted to long-distance flight over open waters.
  • B. Luman
    Luman is a masculine given name of English origin, historically borne by figures such as the 19th-century American art patron Luman Reed.
  • C. Lusei
    Lusei are a major clan of the Mizo people of Northeast India, historically influential in shaping Mizo culture, language, and social organization.
  • D. Cuyonon
    Cuyonon is an Austronesian language spoken primarily by the Cuyonon people of Palawan and nearby islands in the Philippines.
  • E. Cailungo
    Cailungo is a locality within the municipality of Serravalle in the Republic of San Marino.
  • 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: Lusen
Triple: [Bavarian Forest National Park, highestPoint, Lusen]
Generated description
Lusen is a prominent mountain on the German-Czech border in the Bavarian Forest, known for its rocky summit and extensive hiking trails.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lusen
Target entity description: Lusen is a prominent mountain on the German-Czech border in the Bavarian Forest, known for its rocky summit and extensive hiking trails.
  • A. Lugensa
    Lugensa is a genus of seabirds in the petrel family Procellariidae, comprising medium-sized, oceanic birds adapted to long-distance flight over open waters.
  • B. Luman
    Luman is a masculine given name of English origin, historically borne by figures such as the 19th-century American art patron Luman Reed.
  • C. Lusei
    Lusei are a major clan of the Mizo people of Northeast India, historically influential in shaping Mizo culture, language, and social organization.
  • D. Cuyonon
    Cuyonon is an Austronesian language spoken primarily by the Cuyonon people of Palawan and nearby islands in the Philippines.
  • E. Cailungo
    Cailungo is a locality within the municipality of Serravalle in the Republic of San Marino.
  • 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_69ca847870a881909d8d751a7d29da39 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd989788e4819086c235bf37a56b04 completed April 1, 2026, 10:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69d13a5cd2d881908b27649b396c50a1 completed April 4, 2026, 4:20 p.m.
NEDg Description generation batch_69d13be79b1c8190a9110312ae25cf32 completed April 4, 2026, 4:27 p.m.
NED2 Entity disambiguation (via description) batch_69d13ca165b88190b4d629df0e079b3b completed April 4, 2026, 4:30 p.m.
Created at: March 30, 2026, 7:59 p.m.