Triple

T7998465
Position Surface form Disambiguated ID Type / Status
Subject ISSP E186185 entity
Predicate abbreviation P43 FINISHED
Object ISSP E186185 NE FINISHED

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: ISSP | Statement: [ISSP, abbreviation, ISSP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ISSP
Context triple: [ISSP, abbreviation, ISSP]
  • A. ISSP chosen
    ISSP is a renowned research institute of the University of Tokyo specializing in condensed matter and solid state physics.
  • B. IAS
    IAS is India’s premier civil service responsible for administrative leadership and implementation of government policies at the central and state levels.
  • C. IAS
    IAS is the commonly used abbreviation for the Indian Academy of Sciences, a premier scientific society in India dedicated to promoting and advancing science.
  • D. IAS
    IAS is the IATA airport code for Iași International Airport, a major air transport hub serving the city of Iași in northeastern Romania.
  • E. IPS
    IPS is the National Rail station code used to identify Ipswich railway station in Suffolk, England.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca82aaaf24819084b94d18f699ba53 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3c9a12788190a5607a538f4e07c1 completed March 31, 2026, 3:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69cbe114372c819086f06e184d5ebde2 completed March 31, 2026, 2:58 p.m.
Created at: March 30, 2026, 5:17 p.m.