Triple

T1138769
Position Surface form Disambiguated ID Type / Status
Subject Zlín E23399 entity
Predicate twinCity P1072 FINISHED
Object Romans-sur-Isère E56858 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: Romans-sur-Isère | Statement: [Zlín, twinCity, Romans-sur-Isère]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Romans-sur-Isère
Context triple: [Zlín, twinCity, Romans-sur-Isère]
  • A. Romans-sur-Isère chosen
    Romans-sur-Isère is a commune in southeastern France known historically for its shoe-making industry and its location on the banks of the Isère River.
  • B. Vaison-la-Romaine
    Vaison-la-Romaine is a historic town in southeastern France renowned for its extensive Roman archaeological sites and medieval architecture.
  • C. Tarascon
    Tarascon is a historic town in southern France, known for its medieval castle and Provençal heritage along the lower Rhône Valley.
  • D. Auxerre
    Auxerre is a historic city in the Burgundy region of central France, known for its medieval architecture, Gothic cathedral, and role as a regional cultural and economic center.
  • E. Aigues-Mortes
    Aigues-Mortes is a historic fortified town in southern France, renowned for its well-preserved medieval walls and proximity to the salt marshes of the Camargue.
  • 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_69a493ef399c8190b04b9146d2314f59 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4bc25dda481909a26d726fdbdbb50 completed March 1, 2026, 10:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac5eaf952c81908c45b511f0231340 completed March 7, 2026, 5:21 p.m.
Created at: March 1, 2026, 7:44 p.m.