Triple

T4456754
Position Surface form Disambiguated ID Type / Status
Subject Rupel E97745 entity
Predicate flowsPast P4996 FINISHED
Object Schelle
Schelle is a municipality in the Belgian province of Antwerp, situated along the Rupel River.
 E442254 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: Schelle | Statement: [Rupel, flowsPast, Schelle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Schelle
Context triple: [Rupel, flowsPast, Schelle]
  • A. Barbel
    Barbel is a feminine given name, commonly used as a diminutive or variant of names like Barbara in German-speaking regions.
  • B. Schierke
    Schierke is a small village in the Harz Mountains of Germany, known as a gateway to the Brocken peak and for its historic narrow-gauge railway connections and winter sports tourism.
  • C. Strelsau
    Strelsau is the fictional capital city of the kingdom of Ruritania in Anthony Hope’s adventure novel "The Prisoner of Zenda."
  • D. Eisenring
    Eisenring is one of the central arsonists in Max Frisch’s play "Biedermann und die Brandstifter," embodying manipulative and destructive tendencies beneath a seemingly harmless exterior.
  • E. Hoyte
    Hoyte is the first name of Hoyte van Hoytema, a renowned Dutch-Swedish cinematographer known for his work on major films such as "Interstellar" and "Dunkirk."
  • 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: Schelle
Triple: [Rupel, flowsPast, Schelle]
Generated description
Schelle is a municipality in the Belgian province of Antwerp, situated along the Rupel River.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Schelle
Target entity description: Schelle is a municipality in the Belgian province of Antwerp, situated along the Rupel River.
  • A. Barbel
    Barbel is a feminine given name, commonly used as a diminutive or variant of names like Barbara in German-speaking regions.
  • B. Schierke
    Schierke is a small village in the Harz Mountains of Germany, known as a gateway to the Brocken peak and for its historic narrow-gauge railway connections and winter sports tourism.
  • C. Strelsau
    Strelsau is the fictional capital city of the kingdom of Ruritania in Anthony Hope’s adventure novel "The Prisoner of Zenda."
  • D. Eisenring
    Eisenring is one of the central arsonists in Max Frisch’s play "Biedermann und die Brandstifter," embodying manipulative and destructive tendencies beneath a seemingly harmless exterior.
  • E. Hoyte
    Hoyte is the first name of Hoyte van Hoytema, a renowned Dutch-Swedish cinematographer known for his work on major films such as "Interstellar" and "Dunkirk."
  • 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_69b3454777808190b78aa9047ba1f018 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b356434e9481908f883c09e0908f6b completed March 13, 2026, 12:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69b6282743e08190a2c84f3b80c6d260 completed March 15, 2026, 3:31 a.m.
NEDg Description generation batch_69b62af29d3c81908cb82d142c2a55a4 completed March 15, 2026, 3:43 a.m.
NED2 Entity disambiguation (via description) batch_69b62ba4d6c88190b4eaacd09a0b2b66 completed March 15, 2026, 3:46 a.m.
Created at: March 12, 2026, 11:33 p.m.