Triple

T17448201
Position Surface form Disambiguated ID Type / Status
Subject Bridge of Vulci E424840 entity
Predicate locatedNear P294 FINISHED
Object Fiora river 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: Fiora river | Statement: [Bridge of Vulci, locatedNear, Fiora river]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fiora river
Context triple: [Bridge of Vulci, locatedNear, Fiora river]
  • A. Fiora River chosen
    The Fiora River is a watercourse in central Italy that flows through the regions of Tuscany and Lazio before emptying into the Tyrrhenian Sea.
  • B. Fiumorbo River
    The Fiumorbo River is a Corsican watercourse that flows from the island’s central mountains toward its eastern coast, shaping the surrounding valleys and landscapes.
  • C. Fedacla river
    The Fedacla river is a mountain stream in the Upper Engadine region of Switzerland that feeds into Lake Sils.
  • D. Scorff River
    The Scorff River is a coastal river in Brittany, northwestern France, that flows into the Atlantic Ocean near the city of Lorient.
  • E. Itaoca River
    The Itaoca River is a watercourse in southeastern Brazil that ultimately drains into Guanabara Bay near the city of Rio de Janeiro.
  • 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_69d889db0ba481908402409af3b37917 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e44ffe18f08190be023de89e3d7d5c completed April 19, 2026, 3:46 a.m.
Created at: April 10, 2026, 5:47 a.m.