Triple

T5047437
Position Surface form Disambiguated ID Type / Status
Subject Randsfjorden E113700 entity
Predicate inflow P415 FINISHED
Object Etna
Etna is a river in Innlandet county, Norway, known for flowing through the Etnedal valley before emptying into the large lake Randsfjorden.
 E489293 NE FINISHED

How this triple was built (4 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: Etna | Statement: [Randsfjorden, inflow, Etna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Etna
Context triple: [Randsfjorden, inflow, Etna]
  • A. Mount Etna
    Mount Etna is an active stratovolcano on the east coast of Sicily and one of the most active and iconic volcanoes in the world.
  • B. Parco dell'Etna
    Parco dell'Etna is a regional park in Sicily that safeguards the natural landscapes, volcanic features, and biodiversity surrounding Mount Etna.
  • C. Roè Volciano
    Roè Volciano is a municipality in the province of Brescia in Lombardy, northern Italy, situated near Lake Garda.
  • D. Stromboli
    Stromboli is an active volcanic island in the Tyrrhenian Sea, famous for its frequent mild eruptions that have earned it the nickname "Lighthouse of the Mediterranean."
  • E. Stromboli
    Stromboli is the greedy, villainous puppeteer who exploits Pinocchio for profit in Disney’s animated film adaptation of the classic tale.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Etna
Triple: [Randsfjorden, inflow, Etna]
Generated description
Etna is a river in Innlandet county, Norway, known for flowing through the Etnedal valley before emptying into the large lake Randsfjorden.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Etna
Target entity description: Etna is a river in Innlandet county, Norway, known for flowing through the Etnedal valley before emptying into the large lake Randsfjorden.
  • A. Mount Etna
    Mount Etna is an active stratovolcano on the east coast of Sicily and one of the most active and iconic volcanoes in the world.
  • B. Parco dell'Etna
    Parco dell'Etna is a regional park in Sicily that safeguards the natural landscapes, volcanic features, and biodiversity surrounding Mount Etna.
  • C. Roè Volciano
    Roè Volciano is a municipality in the province of Brescia in Lombardy, northern Italy, situated near Lake Garda.
  • D. Stromboli
    Stromboli is an active volcanic island in the Tyrrhenian Sea, famous for its frequent mild eruptions that have earned it the nickname "Lighthouse of the Mediterranean."
  • E. Stromboli
    Stromboli is the greedy, villainous puppeteer who exploits Pinocchio for profit in Disney’s animated film adaptation of the classic tale.
  • F. None of above. chosen

Provenance (5 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_69bd44391fc48190a311ce9c826c209b completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd740002b48190bc7aa176d734c589 completed March 20, 2026, 4:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69be9c9143a081909132c66eb9fc91db completed March 21, 2026, 1:26 p.m.
NEDg Description generation batch_69be9cfeb7a08190b87aef96a31a41cd completed March 21, 2026, 1:28 p.m.
NED2 Entity disambiguation (via description) batch_69bea0cae0bc819098e8312f440ac0ba completed March 21, 2026, 1:44 p.m.
Created at: March 20, 2026, 1:37 p.m.