Triple

T16060041
Position Surface form Disambiguated ID Type / Status
Subject Terres de l’Ebre E389583 entity
Predicate hasImportantTown P14082 FINISHED
Object Móra d’Ebre E389584 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: Móra d’Ebre | Statement: [Terres de l’Ebre, hasImportantTown, Móra d’Ebre]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Móra d’Ebre
Context triple: [Terres de l’Ebre, hasImportantTown, Móra d’Ebre]
  • A. Móra d’Ebre chosen
    Móra d’Ebre is a town in Catalonia, Spain, situated on the Ebro River and serving as an important local administrative and commercial center.
  • B. La Palma d’Ebre
    La Palma d’Ebre is a small municipality in the province of Tarragona, Catalonia, Spain, known for its rural character and Mediterranean landscape.
  • C. Juda
    Juda is the historical name of Ouidah, a coastal city in present-day Benin that was a major center of the transatlantic slave trade.
  • D. Fadiouth
    Fadiouth is a small Senegalese island village known for its shell-covered streets, granaries on stilts, and strong Serer cultural and religious traditions.
  • E. Yehudi
    Yehudi is a masculine given name most famously associated with the renowned violinist Yehudi Menuhin.
  • 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_69d86dae698881908327ef2d67706cb9 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1837850288190910ef37d6484c600 completed April 17, 2026, 12:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbe88a608190bc0a0cbfdb71e81d completed May 10, 2026, 1:14 a.m.
Created at: April 10, 2026, 4:57 a.m.