Triple

T6338034
Position Surface form Disambiguated ID Type / Status
Subject Wda E142540 entity
Predicate mouthLocation P417 FINISHED
Object Świecie
Świecie is a historic town in northern Poland, located in the Kuyavian-Pomeranian Voivodeship and known for its medieval castle and position near the confluence of the Vistula and Wda rivers.
 E586822 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: Świecie | Statement: [Wda, mouthLocation, Świecie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Świecie
Context triple: [Wda, mouthLocation, Świecie]
  • A. Verden
    Verden is a historic town in Lower Saxony, Germany, known for its medieval cathedral and location along the Weser River.
  • B. La Terre
    La Terre is a naturalist novel by Émile Zola that portrays the brutal lives, struggles, and moral decay of French peasants in the 19th century countryside.
  • C. Erdek
    Erdek is a coastal town and popular seaside resort in Turkey’s Balıkesir Province, located on the Kapıdağ Peninsula along the Sea of Marmara.
  • D. Terra
    Terra is a sustainability-themed character created as one of the official mascots for Expo 2020 Dubai, symbolizing environmental awareness and ecological responsibility.
  • E. Maa
    Maa is a Nilotic language spoken primarily by the Maasai people of Kenya and Tanzania.
  • 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: Świecie
Triple: [Wda, mouthLocation, Świecie]
Generated description
Świecie is a historic town in northern Poland, located in the Kuyavian-Pomeranian Voivodeship and known for its medieval castle and position near the confluence of the Vistula and Wda rivers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Świecie
Target entity description: Świecie is a historic town in northern Poland, located in the Kuyavian-Pomeranian Voivodeship and known for its medieval castle and position near the confluence of the Vistula and Wda rivers.
  • A. Verden
    Verden is a historic town in Lower Saxony, Germany, known for its medieval cathedral and location along the Weser River.
  • B. La Terre
    La Terre is a naturalist novel by Émile Zola that portrays the brutal lives, struggles, and moral decay of French peasants in the 19th century countryside.
  • C. Erdek
    Erdek is a coastal town and popular seaside resort in Turkey’s Balıkesir Province, located on the Kapıdağ Peninsula along the Sea of Marmara.
  • D. Terra
    Terra is a sustainability-themed character created as one of the official mascots for Expo 2020 Dubai, symbolizing environmental awareness and ecological responsibility.
  • E. Maa
    Maa is a Nilotic language spoken primarily by the Maasai people of Kenya and Tanzania.
  • 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_69c008d4d8e88190ad301c05b08722ac completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0654e11988190b708426d3003716a completed March 22, 2026, 9:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69c604307b388190bbc59f5f57cb4bbe completed March 27, 2026, 4:14 a.m.
NEDg Description generation batch_69c606cb4d3c8190b8200ee8284cf1e7 completed March 27, 2026, 4:25 a.m.
NED2 Entity disambiguation (via description) batch_69c60741e7388190a8194d168a769cfd completed March 27, 2026, 4:27 a.m.
Created at: March 22, 2026, 4:30 p.m.