Triple

T22326459
Position Surface form Disambiguated ID Type / Status
Subject SSB E551913 entity
Predicate abbreviation P43 FINISHED
Object SSB 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: SSB | Statement: [SSB, abbreviation, SSB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SSB
Context triple: [SSB, abbreviation, SSB]
  • A. SSB
    SSB is one of India's Central Armed Police Forces responsible primarily for guarding the country's borders with Nepal and Bhutan and maintaining internal security.
  • B. SSB
    SSB is the standard abbreviation for the Solar System barycenter, the common center of mass around which all bodies in the Solar System, including the Sun, orbit.
  • C. SSB
    SSB is the national statistical institute of Norway responsible for collecting, analyzing, and publishing official statistics about Norwegian society and the economy.
  • D. SSB
    SSB is the Turkish Presidency of Defense Industries, the government body responsible for managing and developing Turkey’s defense industry and procurement programs.
  • E. SSB
    SSB is the public transport operator serving Stuttgart, Germany, running the city’s light rail, bus, and other local transit services.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

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_69e11e482f788190b78d1588fc26d606 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15768696481909be124e86c23d551 completed April 29, 2026, 12:57 a.m.
Created at: April 16, 2026, 8:42 p.m.