Triple

T4548941
Position Surface form Disambiguated ID Type / Status
Subject Bern tram network E110113 entity
Predicate hasStop P17789 FINISHED
Object Köniz stop
Köniz stop is a public transport stop in the municipality of Köniz that serves passengers on the Bern tram network.
E452076 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: Köniz stop | Statement: [Bern tram network, hasStop, Köniz stop]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Köniz stop
Context triple: [Bern tram network, hasStop, Köniz stop]
  • A. Koni
    Koni is a diminutive form of the given name Konrad, typically used as an affectionate nickname.
  • B. Konerko
    Konerko is the surname of Paul Konerko, a former Major League Baseball first baseman best known for his long tenure and leadership with the Chicago White Sox.
  • C. Kœnig
    Kœnig is a French surname most notably associated with figures such as General Marie-Pierre Kœnig, a prominent military leader during World War II.
  • D. Kileler
    Kileler is a municipality and village in the Thessaly region of central Greece, known historically for its agricultural character and the 1910 peasant uprising.
  • E. Kinnim
    Kinnim is a tractate of the Mishnah that deals with the laws of bird offerings and the complications arising from their possible mix-ups.
  • 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: Köniz stop
Triple: [Bern tram network, hasStop, Köniz stop]
Generated description
Köniz stop is a public transport stop in the municipality of Köniz that serves passengers on the Bern tram network.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Köniz stop
Target entity description: Köniz stop is a public transport stop in the municipality of Köniz that serves passengers on the Bern tram network.
  • A. Koni
    Koni is a diminutive form of the given name Konrad, typically used as an affectionate nickname.
  • B. Konerko
    Konerko is the surname of Paul Konerko, a former Major League Baseball first baseman best known for his long tenure and leadership with the Chicago White Sox.
  • C. Kœnig
    Kœnig is a French surname most notably associated with figures such as General Marie-Pierre Kœnig, a prominent military leader during World War II.
  • D. Kileler
    Kileler is a municipality and village in the Thessaly region of central Greece, known historically for its agricultural character and the 1910 peasant uprising.
  • E. Kinnim
    Kinnim is a tractate of the Mishnah that deals with the laws of bird offerings and the complications arising from their possible mix-ups.
  • 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_69bd4412524c8190be5bcc9ddee91848 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd57f3f8348190868e274ac4df87ce completed March 20, 2026, 2:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdb945bd3881908e6c3f5f91b5f38e completed March 20, 2026, 9:16 p.m.
NEDg Description generation batch_69bdbecf94d0819087519e44aab5a035 completed March 20, 2026, 9:40 p.m.
NED2 Entity disambiguation (via description) batch_69bdbf81f1208190946611fb6a1c20ba completed March 20, 2026, 9:43 p.m.
Created at: March 20, 2026, 1:05 p.m.