Triple

T19016012
Position Surface form Disambiguated ID Type / Status
Subject Enrico Mattei E465350 entity
Predicate employer P7 FINISHED
Object ENI NE NERFINISHED

How this triple was built (2 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: ENI | Statement: [Enrico Mattei, employer, ENI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ENI
Context triple: [Enrico Mattei, employer, ENI]
  • A. ENI chosen
    ENI is a major Italian multinational energy company involved in oil, gas, and renewable energy operations worldwide.
  • B. ENI
    ENI is the European Neighbourhood Instrument, an EU funding mechanism that supports political, economic, and social cooperation with neighboring countries to promote stability and development.
  • C. ENIC Group
    ENIC Group is a British investment company best known for its majority ownership and long-term control of Premier League football club Tottenham Hotspur.
  • D. Cogent Communications
    Cogent Communications is a multinational internet service provider specializing in high-speed fiber-optic connectivity and IP transit services for businesses and carriers.
  • E. Altice USA
    Altice USA is a major American telecommunications and media company that provides cable television, internet, and phone services under brands such as Optimum.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8dd025c188190a1d81f5b4ec7e2c6 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d6db04fc819094709f223e30a526 completed April 20, 2026, 7:33 a.m.
Created at: April 10, 2026, 12:02 p.m.