Triple

T16991238
Position Surface form Disambiguated ID Type / Status
Subject Marjan Hill E412197 entity
Predicate hasLandmark P105 FINISHED
Object Telegrin peak
Telegrin peak is the highest point of Marjan Hill in Split, Croatia, offering panoramic views of the city and the Adriatic Sea.
E1245010 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: Telegrin peak | Statement: [Marjan Hill, hasLandmark, Telegrin peak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Telegrin peak
Context triple: [Marjan Hill, hasLandmark, Telegrin peak]
  • A. Cheshnina Peak
    Cheshnina Peak is a mountain summit located within Alaska’s Wrangell Mountains range.
  • B. Kaleetan Peak
    Kaleetan Peak is a prominent mountain in Washington State’s Cascade Range, known for its rugged terrain and popular hiking and climbing routes.
  • C. Truuli Peak
    Truuli Peak is the highest mountain in Alaska’s Kenai Mountains, known for its remote, glaciated terrain on the Kenai Peninsula.
  • D. Thulagi Peak
    Thulagi Peak is a prominent mountain in the Nepalese Himalayas, known for its challenging climbing routes and proximity to Manaslu.
  • E. Hohneck peak
    Hohneck peak is one of the highest and most prominent summits in the Vosges Mountains of northeastern France, known for its panoramic views and popular hiking and skiing areas.
  • 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: Telegrin peak
Triple: [Marjan Hill, hasLandmark, Telegrin peak]
Generated description
Telegrin peak is the highest point of Marjan Hill in Split, Croatia, offering panoramic views of the city and the Adriatic Sea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Telegrin peak
Target entity description: Telegrin peak is the highest point of Marjan Hill in Split, Croatia, offering panoramic views of the city and the Adriatic Sea.
  • A. Cheshnina Peak
    Cheshnina Peak is a mountain summit located within Alaska’s Wrangell Mountains range.
  • B. Kaleetan Peak
    Kaleetan Peak is a prominent mountain in Washington State’s Cascade Range, known for its rugged terrain and popular hiking and climbing routes.
  • C. Truuli Peak
    Truuli Peak is the highest mountain in Alaska’s Kenai Mountains, known for its remote, glaciated terrain on the Kenai Peninsula.
  • D. Thulagi Peak
    Thulagi Peak is a prominent mountain in the Nepalese Himalayas, known for its challenging climbing routes and proximity to Manaslu.
  • E. Hohneck peak
    Hohneck peak is one of the highest and most prominent summits in the Vosges Mountains of northeastern France, known for its panoramic views and popular hiking and skiing areas.
  • 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_69d886cb581c8190ab05f4b429c9cd85 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d280e3348190a27bd5dc7cf87c0e completed April 18, 2026, 6:50 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00dc14d5688190945f7ae72f724922 completed May 10, 2026, 7:27 p.m.
NEDg Description generation batch_6a0114d5aeb0819086f1a5d279ac0d0f completed May 10, 2026, 11:29 p.m.
NED2 Entity disambiguation (via description) batch_6a0115c967b0819088e2335fd45d755b completed May 10, 2026, 11:33 p.m.
Created at: April 10, 2026, 5:32 a.m.