Triple

T3297237
Position Surface form Disambiguated ID Type / Status
Subject Abruzzo E69244 entity
Predicate capital P234 FINISHED
Object L'Aquila
L'Aquila is a historic city in central Italy known for its medieval architecture and as the administrative and cultural center of the surrounding mountainous region.
E347601 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: L'Aquila | Statement: [Abruzzo, capital, L'Aquila]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: L'Aquila
Context triple: [Abruzzo, capital, L'Aquila]
  • A. Frosinone
    Frosinone is a city in central Italy that serves as the capital of the province of the same name within the Lazio region.
  • B. Isernia
    Isernia is a historic town and provincial capital in the Molise region of southern-central Italy, known for its ancient Samnite and Roman roots.
  • C. Rieti
    Rieti is a historic town in central Italy often considered the geographical center of the country and known for its medieval architecture and proximity to the Apennine Mountains.
  • D. Teramo
    Teramo is a historic city in the Abruzzo region of central Italy, known for its Roman archaeological remains and medieval architecture.
  • E. Civitanova Marche
    Civitanova Marche is a coastal town and popular seaside resort on the Adriatic Sea in the Marche region of central Italy.
  • 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: L'Aquila
Triple: [Abruzzo, capital, L'Aquila]
Generated description
L'Aquila is a historic city in central Italy known for its medieval architecture and as the administrative and cultural center of the surrounding mountainous region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: L'Aquila
Target entity description: L'Aquila is a historic city in central Italy known for its medieval architecture and as the administrative and cultural center of the surrounding mountainous region.
  • A. Frosinone
    Frosinone is a city in central Italy that serves as the capital of the province of the same name within the Lazio region.
  • B. Isernia
    Isernia is a historic town and provincial capital in the Molise region of southern-central Italy, known for its ancient Samnite and Roman roots.
  • C. Rieti
    Rieti is a historic town in central Italy often considered the geographical center of the country and known for its medieval architecture and proximity to the Apennine Mountains.
  • D. Teramo
    Teramo is a historic city in the Abruzzo region of central Italy, known for its Roman archaeological remains and medieval architecture.
  • E. Civitanova Marche
    Civitanova Marche is a coastal town and popular seaside resort on the Adriatic Sea in the Marche region of central Italy.
  • 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_69ad859e529c8190a404273f53cb487d completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb078f3dc8190afb624f62894e48f completed March 8, 2026, 5:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2f3d35c448190a4ca50ae31639e65 completed March 12, 2026, 5:11 p.m.
NEDg Description generation batch_69b2f9fb060881909dd940c69cf4a12e completed March 12, 2026, 5:38 p.m.
NED2 Entity disambiguation (via description) batch_69b3137bf988819080cef6c1946ec622 completed March 12, 2026, 7:26 p.m.
Created at: March 8, 2026, 3:10 p.m.