Triple

T4585204
Position Surface form Disambiguated ID Type / Status
Subject Gran Paradiso massif E101950 entity
Predicate containsPeak P8205 FINISHED
Object Punta Ondezana
Punta Ondezana is a mountain peak in the Italian Alps that forms part of the Gran Paradiso massif.
E454668 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: Punta Ondezana | Statement: [Gran Paradiso massif, containsPeak, Punta Ondezana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Punta Ondezana
Context triple: [Gran Paradiso massif, containsPeak, Punta Ondezana]
  • A. Punta La Marmora
    Punta La Marmora is the tallest mountain in Sardinia, Italy, located in the Gennargentu range and known for its panoramic views over the island.
  • B. Punta Raisi
    Punta Raisi is a coastal area in the municipality of Cinisi, near Palermo in Sicily, known primarily as the site of Palermo’s main international airport.
  • C. Punta Brava
    Punta Brava is a locality in Cuba historically known as the site where independence leader Antonio Maceo was killed in battle.
  • D. Punta de Vacas
    Punta de Vacas is a small settlement in Argentina’s Mendoza province, located in the Andes and commonly used as a base for travelers heading toward Aconcagua and other high-mountain destinations.
  • E. Punta Fourà
    Punta Fourà is a mountain peak in the Italian Alps that forms part of the Gran Paradiso massif.
  • 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: Punta Ondezana
Triple: [Gran Paradiso massif, containsPeak, Punta Ondezana]
Generated description
Punta Ondezana is a mountain peak in the Italian Alps that forms part of the Gran Paradiso massif.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Punta Ondezana
Target entity description: Punta Ondezana is a mountain peak in the Italian Alps that forms part of the Gran Paradiso massif.
  • A. Punta La Marmora
    Punta La Marmora is the tallest mountain in Sardinia, Italy, located in the Gennargentu range and known for its panoramic views over the island.
  • B. Punta Raisi
    Punta Raisi is a coastal area in the municipality of Cinisi, near Palermo in Sicily, known primarily as the site of Palermo’s main international airport.
  • C. Punta Brava
    Punta Brava is a locality in Cuba historically known as the site where independence leader Antonio Maceo was killed in battle.
  • D. Punta de Vacas
    Punta de Vacas is a small settlement in Argentina’s Mendoza province, located in the Andes and commonly used as a base for travelers heading toward Aconcagua and other high-mountain destinations.
  • E. Punta Fourà chosen
    Punta Fourà is a mountain peak in the Italian Alps that forms part of the Gran Paradiso massif.
  • F. None of above.

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_69bd43d4ce208190b53158c882b222e3 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd59056bb48190ba1e0b5beda9bdc4 completed March 20, 2026, 2:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfa33103081909e83155f712b821f completed March 21, 2026, 1:53 a.m.
NEDg Description generation batch_69bdfc87fd3881909f072cd85d6b58c2 completed March 21, 2026, 2:03 a.m.
NED2 Entity disambiguation (via description) batch_69bdfcfb3de08190b9345e36c5c0c01c completed March 21, 2026, 2:05 a.m.
Created at: March 20, 2026, 1:10 p.m.