Triple

T13114114
Position Surface form Disambiguated ID Type / Status
Subject Vorpommern-Greifswald E311048 entity
Predicate contains P35 FINISHED
Object Loitz
Loitz is a small town in northeastern Germany situated in the state of Mecklenburg-Vorpommern.
 E1021597 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: Loitz | Statement: [Vorpommern-Greifswald, contains, Loitz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Loitz
Context triple: [Vorpommern-Greifswald, contains, Loitz]
  • A. Loerzer
    Loerzer is the surname of Bruno Loerzer, a notable German First World War flying ace and later Luftwaffe general.
  • B. Lotha
    Lotha is a Naga ethnic group primarily inhabiting the Wokha district of Nagaland in Northeast India, known for its rich cultural traditions and festivals.
  • C. Marloffstein
    Marloffstein is a small municipality in the Erlangen-Höchstadt district of Bavaria, Germany, known for its rural character and proximity to the city of Erlangen.
  • D. Leyhof
    Leyhof is a residential neighborhood in the Dutch town of Leiderdorp, located in the province of South Holland.
  • E. Lieberher
    Lieberher is the surname of American actor Jaeden Lieberher, known for his roles in films like "St. Vincent" and "It."
  • 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: Loitz
Triple: [Vorpommern-Greifswald, contains, Loitz]
Generated description
Loitz is a small town in northeastern Germany situated in the state of Mecklenburg-Vorpommern.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Loitz
Target entity description: Loitz is a small town in northeastern Germany situated in the state of Mecklenburg-Vorpommern.
  • A. Loerzer
    Loerzer is the surname of Bruno Loerzer, a notable German First World War flying ace and later Luftwaffe general.
  • B. Lotha
    Lotha is a Naga ethnic group primarily inhabiting the Wokha district of Nagaland in Northeast India, known for its rich cultural traditions and festivals.
  • C. Marloffstein
    Marloffstein is a small municipality in the Erlangen-Höchstadt district of Bavaria, Germany, known for its rural character and proximity to the city of Erlangen.
  • D. Leyhof
    Leyhof is a residential neighborhood in the Dutch town of Leiderdorp, located in the province of South Holland.
  • E. Lieberher
    Lieberher is the surname of American actor Jaeden Lieberher, known for his roles in films like "St. Vincent" and "It."
  • 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_69d806a872d08190a329806f8ff30df4 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d9817f8ee8819084078b4bec5e4f18 completed April 10, 2026, 11:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6e28105c481908781775ba489c296 completed May 3, 2026, 5:52 a.m.
NEDg Description generation batch_69f6e33f44208190881bee81c2a41850 completed May 3, 2026, 5:55 a.m.
NED2 Entity disambiguation (via description) batch_69f6e407dd988190b928b8931985a815 completed May 3, 2026, 5:58 a.m.
Created at: April 9, 2026, 9:06 p.m.