Triple

T15957358
Position Surface form Disambiguated ID Type / Status
Subject ES Tunis E386969 entity
Predicate homeStadiumCity P5282 FINISHED
Object Radès E394133 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: Radès | Statement: [ES Tunis, homeStadiumCity, Radès]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Radès
Context triple: [ES Tunis, homeStadiumCity, Radès]
  • A. Radès chosen
    Radès is a coastal city in northern Tunisia known for its major sports facilities, including the national stadium that hosts prominent football clubs and international events.
  • B. Benslimane
    Benslimane is a town and provincial capital in northwestern Morocco, known for its forests and proximity to Casablanca.
  • C. Boucha
    Boucha is the surname of Henry Boucha, a notable American ice hockey player of Ojibwe heritage.
  • D. Maaloula
    Maaloula is a historic Syrian mountain village renowned as one of the last places where Western Neo-Aramaic, a modern descendant of the language of Jesus, is still spoken.
  • E. Boujad
    Boujad is a town in central Morocco known for its traditional crafts and cultural heritage.
  • 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_69d86da882448190a82ea962fe343b79 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156fc6f348190b49c4858281a0904 completed April 16, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffc3c3aae081909366c01b3fec4d47 completed May 9, 2026, 11:31 p.m.
Created at: April 10, 2026, 4:53 a.m.