Triple

T4113708
Position Surface form Disambiguated ID Type / Status
Subject Turku E90238 entity
Predicate hasRiver P165 FINISHED
Object Aura River E413223 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: Aura River | Statement: [Turku, hasRiver, Aura River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aura River
Context triple: [Turku, hasRiver, Aura River]
  • A. Aura River chosen
    The Aura River is a significant waterway in southwestern Finland that flows through the city of Turku and into the Archipelago Sea.
  • B. River Ember
    The River Ember is a small watercourse in Surrey, England, that branches from and later rejoins the River Mole before flowing toward the River Thames.
  • C. Castalian Spring
    Castalian Spring is the sacred fountain at Delphi in ancient Greece, where pilgrims and priests ritually purified themselves before consulting the Oracle of Apollo.
  • D. Sacred Spring
    Sacred Spring is the natural hot water source at the heart of the Roman Baths in Bath, England, long revered as a place of ritual and healing.
  • E. Light River
    Light River is a river in South Australia that flows through agricultural regions before emptying into Gulf St Vincent.
  • 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_69aed95c080881908125e30c5dcdc6f8 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af01e06ce48190b840d931e44095ea completed March 9, 2026, 5:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69b576a9158c8190aa0068d955fb174d completed March 14, 2026, 2:54 p.m.
Created at: March 9, 2026, 3:41 p.m.