Triple

T22514831
Position Surface form Disambiguated ID Type / Status
Subject Piedmont railway network E556613 entity
Predicate connectsCity P4245 FINISHED
Object Susa 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: Susa | Statement: [Piedmont railway network, connectsCity, Susa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susa
Context triple: [Piedmont railway network, connectsCity, Susa]
  • A. Susa
    Susa was an ancient city in southwestern Iran that served as a major political and administrative center for several empires, including the Achaemenid Persians.
  • B. Susa chosen
    Susa is an ancient town in the Piedmont region of northwestern Italy, historically significant as a key Alpine gateway between Italy and France.
  • C. Susa
    Susa is a coastal town in northeastern Libya known for its ancient Greek and Roman archaeological remains and its location along the Mediterranean Sea.
  • D. Ecbatana
    Ecbatana is an ancient city, traditionally identified with the capital of the Median Empire in northwestern Iran, known from classical sources and biblical texts.
  • E. Arsanjan
    Arsanjan is a small city in southern Iran known for its agricultural activities and location within the historical and culturally rich Fars region.
  • 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_69e11e555edc81909ca803587dafd747 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15e2c3098819098a553133cc9515b completed April 29, 2026, 1:26 a.m.
Created at: April 16, 2026, 8:50 p.m.