Triple

T4620460
Position Surface form Disambiguated ID Type / Status
Subject Sömmerda E100965 entity
Predicate vehicleRegistrationCode P1173 FINISHED
Object SÖM
SÖM is the vehicle registration code for the Sömmerda district in the German state of Thuringia.
 E459206 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: SÖM | Statement: [Sömmerda, vehicleRegistrationCode, SÖM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SÖM
Context triple: [Sömmerda, vehicleRegistrationCode, SÖM]
  • A. Somosomo
    Somosomo is a coastal village on the Fijian island of Taveuni, known as a traditional center of chiefly authority and local administration.
  • B. сомони
    сомони — это денежная единица Таджикистана, названная в честь основателя таджикской государственности Исмоили Сомони.
  • C. SOU
    SOU is the three-letter IATA airport code for Southampton Airport in Hampshire, England.
  • D. Sowams
    Sowams was a principal Wampanoag village and homeland in present-day New England, historically significant as the seat of the sachem Massasoit and an early site of Native–Pilgrim interaction.
  • E. SOM I
    SOM I is the first installment in the SOM series, serving as the initial part that precedes SOM II.
  • 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: SÖM
Triple: [Sömmerda, vehicleRegistrationCode, SÖM]
Generated description
SÖM is the vehicle registration code for the Sömmerda district in the German state of Thuringia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SÖM
Target entity description: SÖM is the vehicle registration code for the Sömmerda district in the German state of Thuringia.
  • A. Somosomo
    Somosomo is a coastal village on the Fijian island of Taveuni, known as a traditional center of chiefly authority and local administration.
  • B. сомони
    сомони — это денежная единица Таджикистана, названная в честь основателя таджикской государственности Исмоили Сомони.
  • C. SOU
    SOU is the three-letter National Rail station code for Southampton Central railway station in Hampshire, England.
  • D. SOU
    SOU is the three-letter IATA airport code for Southampton Airport in Hampshire, England.
  • E. Sowams
    Sowams was a principal Wampanoag village and homeland in present-day New England, historically significant as the seat of the sachem Massasoit and an early site of Native–Pilgrim interaction.
  • 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_69bd43cf363c819087fd5ab441b4a3f4 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd59e560f481908abb1a97b4ff5795 completed March 20, 2026, 2:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfa95bd6c8190ad33e52b338560a6 completed March 21, 2026, 1:55 a.m.
NEDg Description generation batch_69bdfb5502c48190b7679941b83e6e0c completed March 21, 2026, 1:58 a.m.
NED2 Entity disambiguation (via description) batch_69bdff53680c8190a62aace0f0c9f3b3 completed March 21, 2026, 2:15 a.m.
Created at: March 20, 2026, 1:12 p.m.