Triple

T3770013
Position Surface form Disambiguated ID Type / Status
Subject IVASS E82774 entity
Predicate predecessor P97 FINISHED
Object ISVAP
ISVAP was the former Italian supervisory authority responsible for regulating and overseeing the insurance sector before being replaced by IVASS.
E386350 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: ISVAP | Statement: [IVASS, predecessor, ISVAP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ISVAP
Context triple: [IVASS, predecessor, ISVAP]
  • A. IDEP
    IDEP is a regional training and research institute under the United Nations Economic Commission for Africa that focuses on economic development and planning in African countries.
  • B. ISD
    ISD is the abbreviated name for the Intelligence and Security Division, a governmental body responsible for intelligence gathering and national security functions.
  • C. IPS
    IPS is the premier all-India civil service responsible for leadership and command of police forces and law enforcement agencies across India.
  • D. IPS
    IPS is a professional society within the IEEE focused on the science and technology of light, including photonics and optoelectronics.
  • E. IS
    IS is the two-letter ISO 3166-1 alpha-2 country code representing Iceland in international standards and systems.
  • 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: ISVAP
Triple: [IVASS, predecessor, ISVAP]
Generated description
ISVAP was the former Italian supervisory authority responsible for regulating and overseeing the insurance sector before being replaced by IVASS.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: ISVAP
Target entity description: ISVAP was the former Italian supervisory authority responsible for regulating and overseeing the insurance sector before being replaced by IVASS.
  • A. IDEP
    IDEP is a regional training and research institute under the United Nations Economic Commission for Africa that focuses on economic development and planning in African countries.
  • B. ISD
    ISD is the abbreviated name for the Intelligence and Security Division, a governmental body responsible for intelligence gathering and national security functions.
  • C. IPS
    IPS is the premier all-India civil service responsible for leadership and command of police forces and law enforcement agencies across India.
  • D. IPS
    IPS is a professional society within the IEEE focused on the science and technology of light, including photonics and optoelectronics.
  • E. IS
    IS is the two-letter ISO 3166-1 alpha-2 country code representing Iceland in international standards and systems.
  • 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_69ad8b207b0081909d2b48843fbd8795 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adcc2f016c81909c2e3c85dbc3c259 completed March 8, 2026, 7:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4e5287908819084319b8dfa407635 completed March 14, 2026, 4:33 a.m.
NEDg Description generation batch_69b4e61c8dc881908e298528b1e42c0c completed March 14, 2026, 4:37 a.m.
NED2 Entity disambiguation (via description) batch_69b4e686bf2c8190aac01d6c1014c1d4 completed March 14, 2026, 4:39 a.m.
Created at: March 8, 2026, 3:35 p.m.