Triple

T16060475
Position Surface form Disambiguated ID Type / Status
Subject La Serra d’Almos E389595 entity
Predicate roadAccessFrom P22549 FINISHED
Object Tivissa E389591 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: Tivissa | Statement: [La Serra d’Almos, roadAccessFrom, Tivissa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tivissa
Context triple: [La Serra d’Almos, roadAccessFrom, Tivissa]
  • A. Tivissa chosen
    Tivissa is a historic village in Catalonia, Spain, known for its scenic setting among the mountains of the Ribera d’Ebre region and its well-preserved medieval core.
  • B. Buranda
    Buranda is an inner-city suburb of Brisbane, Queensland, known for its major transport interchange and proximity to hospitals and shopping centres.
  • C. Tivim
    Tivim is a village in North Goa, India, known primarily for its railway station on the Konkan Railway that serves as a key transit point for the region.
  • D. Lanassa
    Lanassa was an ancient Greek noblewoman, daughter of Agathocles of Syracuse, who became queen through her marriage to the Hellenistic ruler Pyrrhus of Epirus.
  • E. Wurtulla
    Wurtulla is a coastal suburb on Queensland’s Sunshine Coast in Australia, known for its long sandy beaches and residential communities.
  • 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_69ffe47a92608190993fe7f2c5957019 completed May 10, 2026, 1:50 a.m.
Created at: April 10, 2026, 4:57 a.m.