Triple

T5498874
Position Surface form Disambiguated ID Type / Status
Subject Swiss Federal Roads Office E144276 entity
Predicate usesAbbreviation P43 FINISHED
Object ASTRA E531330 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: ASTRA | Statement: [Swiss Federal Roads Office, usesAbbreviation, ASTRA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ASTRA
Context triple: [Swiss Federal Roads Office, usesAbbreviation, ASTRA]
  • A. ASTRA chosen
    ASTRA is the abbreviated name of Switzerland’s Federal Roads Office, the national authority responsible for the country’s road infrastructure and traffic management.
  • B. Astra
    Astra is a prominent Asian work, likely a creative or literary piece, recognized for its cultural and artistic significance within Asia.
  • C. Astra Planeta
    Astra Planeta are the personified star and planet deities of ancient Greek mythology, often depicted as radiant celestial gods associated with the night sky.
  • D. ASTRO
    ASTRO is the leading professional organization in the United States for radiation oncologists and other specialists involved in radiation therapy for cancer and other diseases.
  • E. Aster 30
    Aster 30 is a long-range, ship- and land-based surface-to-air missile designed for advanced air and missile defense against aircraft, drones, and ballistic threats.
  • 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_69c008f5a2748190bce7a39aabf87a6d completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c01b9050d08190b0cfcfdb5d414476 completed March 22, 2026, 4:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69c04c9c78308190935c3fbbaff08b70 completed March 22, 2026, 8:10 p.m.
Created at: March 22, 2026, 3:32 p.m.