Triple

T9364796
Position Surface form Disambiguated ID Type / Status
Subject Province of Salerno E225372 entity
Predicate includesTown P847 FINISHED
Object Sapri
Sapri is a coastal town in southern Italy known for its scenic Gulf of Policastro setting and role as a seaside resort in the Campania region.
 E794766 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: Sapri | Statement: [Province of Salerno, includesTown, Sapri]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sapri
Context triple: [Province of Salerno, includesTown, Sapri]
  • A. Sapê
    Sapê is a municipality in the state of Paraíba, Brazil, known for its agricultural activities and role in the region’s economic and cultural life.
  • B. Sabya
    Sabya is a city in southwestern Saudi Arabia located within the Jazan Region near the Red Sea coast.
  • C. Safsufa
    Safsufa is a small village in northern Israel, located in the Upper Galilee region near Mount Meron.
  • D. Sangaride
    Sangaride is a mythological figure best known as the beloved of Atys in ancient legends and later operatic adaptations.
  • E. Shastina
    Shastina is a prominent satellite cone and secondary peak on the western flank of California’s Mount Shasta, formed by later volcanic activity.
  • 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: Sapri
Triple: [Province of Salerno, includesTown, Sapri]
Generated description
Sapri is a coastal town in southern Italy known for its scenic Gulf of Policastro setting and role as a seaside resort in the Campania region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sapri
Target entity description: Sapri is a coastal town in southern Italy known for its scenic Gulf of Policastro setting and role as a seaside resort in the Campania region.
  • A. Sapê
    Sapê is a municipality in the state of Paraíba, Brazil, known for its agricultural activities and role in the region’s economic and cultural life.
  • B. Sabya
    Sabya is a city in southwestern Saudi Arabia located within the Jazan Region near the Red Sea coast.
  • C. Safsufa
    Safsufa is a small village in northern Israel, located in the Upper Galilee region near Mount Meron.
  • D. Sangaride
    Sangaride is a mythological figure best known as the beloved of Atys in ancient legends and later operatic adaptations.
  • E. Shastina
    Shastina is a prominent satellite cone and secondary peak on the western flank of California’s Mount Shasta, formed by later volcanic activity.
  • 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_69ca842bdd648190904131d58620d448 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd503fd7f081909655e2a880c84834 completed April 1, 2026, 5:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69d0f3f3c420819084b65fd4537aaf93 completed April 4, 2026, 11:20 a.m.
NEDg Description generation batch_69d0f619e91081909c2ec17e89376295 completed April 4, 2026, 11:29 a.m.
NED2 Entity disambiguation (via description) batch_69d0f6ce1a0c8190aca34958935e0e59 completed April 4, 2026, 11:32 a.m.
Created at: March 30, 2026, 7:42 p.m.