Triple

T17134303
Position Surface form Disambiguated ID Type / Status
Subject Val Camonica E415796 entity
Predicate hasMajorTown P316 FINISHED
Object Capo di Ponte
Capo di Ponte is a town in northern Italy’s Lombardy region, noted for its rich prehistoric rock carvings and archaeological sites within Val Camonica.
E1252399 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: Capo di Ponte | Statement: [Val Camonica, hasMajorTown, Capo di Ponte]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Capo di Ponte
Context triple: [Val Camonica, hasMajorTown, Capo di Ponte]
  • A. Capo Caccia
    Capo Caccia is a dramatic limestone promontory on the northwest coast of Sardinia, Italy, known for its towering cliffs, sea caves, and scenic coastal views.
  • B. Bonacca
    Bonacca is the main town and population center on the Caribbean island of Guanaja in Honduras.
  • C. Via Flacca
    Via Flacca was an ancient Roman coastal road in Latium that linked key towns such as Formiae along the Tyrrhenian Sea.
  • D. Bisacquino
    Bisacquino is a small town in the Sicilian province of Palermo, Italy, known as the birthplace of film director Frank Capra.
  • E. Val Cavallina
    Val Cavallina is a scenic valley in the Lombardy region of northern Italy, known for its lakes, hills, and small historic towns.
  • 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: Capo di Ponte
Triple: [Val Camonica, hasMajorTown, Capo di Ponte]
Generated description
Capo di Ponte is a town in northern Italy’s Lombardy region, noted for its rich prehistoric rock carvings and archaeological sites within Val Camonica.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Capo di Ponte
Target entity description: Capo di Ponte is a town in northern Italy’s Lombardy region, noted for its rich prehistoric rock carvings and archaeological sites within Val Camonica.
  • A. Capo Caccia
    Capo Caccia is a dramatic limestone promontory on the northwest coast of Sardinia, Italy, known for its towering cliffs, sea caves, and scenic coastal views.
  • B. Bonacca
    Bonacca is the main town and population center on the Caribbean island of Guanaja in Honduras.
  • C. Via Flacca
    Via Flacca was an ancient Roman coastal road in Latium that linked key towns such as Formiae along the Tyrrhenian Sea.
  • D. Bisacquino
    Bisacquino is a small town in the Sicilian province of Palermo, Italy, known as the birthplace of film director Frank Capra.
  • E. Val Cavallina
    Val Cavallina is a scenic valley in the Lombardy region of northern Italy, known for its lakes, hills, and small historic towns.
  • 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_69d886d15af4819092f92f8a129763e6 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3f02cbb7881908aa69c3443d149d5 completed April 18, 2026, 8:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a014150d63081908a5614f85694e57a completed May 11, 2026, 2:39 a.m.
NEDg Description generation batch_6a0141e96e4481908bfdf7a1eb4ac979 completed May 11, 2026, 2:41 a.m.
NED2 Entity disambiguation (via description) batch_6a01428ca86881909b18bcfc1c223f22 completed May 11, 2026, 2:44 a.m.
Created at: April 10, 2026, 5:36 a.m.