Triple

T19422400
Position Surface form Disambiguated ID Type / Status
Subject River Seseke E485888 entity
Predicate hasNameInLanguage P15 FINISHED
Object Seseke (German)
Seseke (German) is the German name for the Seseke, a river in North Rhine-Westphalia, Germany, that flows through the eastern Ruhr area.
E1375892 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: Seseke (German) | Statement: [River Seseke, hasNameInLanguage, Seseke (German)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Seseke (German)
Context triple: [River Seseke, hasNameInLanguage, Seseke (German)]
  • A. Sillein (German)
    Sillein is the historical German name for the Slovak city of Žilina, an important regional center in northwestern Slovakia.
  • B. Enz (German)
    Enz (German) is the German name for the Enz River, a tributary of the Neckar flowing through the city of Pforzheim in southwestern Germany.
  • C. Schier (German)
    Schier is the German name for the Chiers, a river in Western Europe that flows through Belgium, Luxembourg, and France.
  • D. Kniphausen (German)
    Kniphausen (German) is the German name for a locality or historical territory in northern Germany, likely associated with the region of East Frisia.
  • E. Sekke
    Sekke is a Japanese noble family branch associated with the prestigious Konoe lineage of the Fujiwara clan.
  • 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: Seseke (German)
Triple: [River Seseke, hasNameInLanguage, Seseke (German)]
Generated description
Seseke (German) is the German name for the Seseke, a river in North Rhine-Westphalia, Germany, that flows through the eastern Ruhr area.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Seseke (German)
Target entity description: Seseke (German) is the German name for the Seseke, a river in North Rhine-Westphalia, Germany, that flows through the eastern Ruhr area.
  • A. Sillein (German)
    Sillein is the historical German name for the Slovak city of Žilina, an important regional center in northwestern Slovakia.
  • B. Enz (German)
    Enz (German) is the German name for the Enz River, a tributary of the Neckar flowing through the city of Pforzheim in southwestern Germany.
  • C. Schier (German)
    Schier is the German name for the Chiers, a river in Western Europe that flows through Belgium, Luxembourg, and France.
  • D. Kniphausen (German)
    Kniphausen (German) is the German name for a locality or historical territory in northern Germany, likely associated with the region of East Frisia.
  • E. Sekke
    Sekke is a Japanese noble family branch associated with the prestigious Konoe lineage of the Fujiwara clan.
  • 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_69d8e8d688f881909c85104a62e09d8a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e632159d7081909d004544ec5992c0 completed April 20, 2026, 2:03 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0733d1d4148190b7dae069a76e7041 completed May 15, 2026, 2:55 p.m.
NEDg Description generation batch_6a0735ce9a348190af1d3f58f1bb26cd completed May 15, 2026, 3:03 p.m.
NED2 Entity disambiguation (via description) batch_6a0736c250708190a6f9ac2364038432 completed May 15, 2026, 3:07 p.m.
Created at: April 10, 2026, 1:37 p.m.