Triple

T12666925
Position Surface form Disambiguated ID Type / Status
Subject Province of Matera E302575 entity
Predicate hasMunicipality P847 FINISHED
Object Irsina
Irsina is a historic hilltop town in the Basilicata region of southern Italy, known for its medieval architecture and panoramic views over the surrounding countryside.
 E996086 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: Irsina | Statement: [Province of Matera, hasMunicipality, Irsina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Irsina
Context triple: [Province of Matera, hasMunicipality, Irsina]
  • A. Irra
    Irra is a Mesopotamian god associated with war, plague, and destruction, often regarded as a fierce aspect or manifestation of the underworld deity Nergal.
  • B. Iaru
    Iaru is the ancient Egyptian paradise-like afterlife realm, often depicted as fertile reed fields where the blessed dead live eternally.
  • C. Gisir
    Gisir is a Bantu language spoken in Central Africa, closely related to and geographically adjacent to Myene.
  • D. Arispe
    Arispe is a small unincorporated rural community located in Ringgold County, Iowa.
  • E. Lovina
    Lovina is a coastal tourist area in northern Bali, Indonesia, known for its black sand beaches, calm seas, and dolphin-watching tours.
  • 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: Irsina
Triple: [Province of Matera, hasMunicipality, Irsina]
Generated description
Irsina is a historic hilltop town in the Basilicata region of southern Italy, known for its medieval architecture and panoramic views over the surrounding countryside.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Irsina
Target entity description: Irsina is a historic hilltop town in the Basilicata region of southern Italy, known for its medieval architecture and panoramic views over the surrounding countryside.
  • A. Irra
    Irra is a Mesopotamian god associated with war, plague, and destruction, often regarded as a fierce aspect or manifestation of the underworld deity Nergal.
  • B. Iaru
    Iaru is the ancient Egyptian paradise-like afterlife realm, often depicted as fertile reed fields where the blessed dead live eternally.
  • C. Gisir
    Gisir is a Bantu language spoken in Central Africa, closely related to and geographically adjacent to Myene.
  • D. Arispe
    Arispe is a small unincorporated rural community located in Ringgold County, Iowa.
  • E. Lovina
    Lovina is a coastal tourist area in northern Bali, Indonesia, known for its black sand beaches, calm seas, and dolphin-watching tours.
  • 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_69d7bded71a88190bb76e2413af9ea66 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96181c40481908f3e2717f5472b85 completed April 10, 2026, 8:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6688a19148190b8d252d3706d2b05 completed May 2, 2026, 9:11 p.m.
NEDg Description generation batch_69f669f746188190b6a86c6aac622701 completed May 2, 2026, 9:17 p.m.
NED2 Entity disambiguation (via description) batch_69f66b18e68881908bf79ab52bcc909e completed May 2, 2026, 9:22 p.m.
Created at: April 9, 2026, 5:20 p.m.