Triple

T118350
Position Surface form Disambiguated ID Type / Status
Subject Deutsche Mark E2391 entity
Predicate ISO4217Code P189 FINISHED
Object DEM
DEM is the former official currency code for the Deutsche Mark, which was Germany’s national currency before the adoption of the euro.
 E12914 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: DEM | Statement: [Deutsche Mark, ISO4217Code, DEM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: DEM
Context triple: [Deutsche Mark, ISO4217Code, DEM]
  • A. DAL
    DAL is the stock ticker symbol for Delta Air Lines, a major U.S.-based international airline.
  • B. DESE
    DESE is the state agency responsible for overseeing public elementary and secondary education in Massachusetts, including standards, accountability, and school support.
  • C. DL
    DL is the two-letter IATA airline designator used to identify Delta Air Lines on tickets, schedules, and flight information.
  • D. DS
    DS is the Directorate of Support, a key administrative and logistical branch responsible for providing essential support services within an intelligence or governmental organization.
  • E. DEC
    DEC is the New York State agency responsible for conserving, improving, and protecting the state's natural resources and environment.
  • 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: DEM
Triple: [Deutsche Mark, ISO4217Code, DEM]
Generated description
DEM is the former official currency code for the Deutsche Mark, which was Germany’s national currency before the adoption of the euro.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: DEM
Target entity description: DEM is the former official currency code for the Deutsche Mark, which was Germany’s national currency before the adoption of the euro.
  • A. DAL
    DAL is the stock ticker symbol for Delta Air Lines, a major U.S.-based international airline.
  • B. DESE
    DESE is the state agency responsible for overseeing public elementary and secondary education in Massachusetts, including standards, accountability, and school support.
  • C. DL
    DL is the two-letter IATA airline designator used to identify Delta Air Lines on tickets, schedules, and flight information.
  • D. DS
    DS is the Directorate of Support, a key administrative and logistical branch responsible for providing essential support services within an intelligence or governmental organization.
  • E. DEC
    DEC is the New York State agency responsible for conserving, improving, and protecting the state's natural resources and environment.
  • 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_69a2506c5428819085c28a8884790e29 completed Feb. 28, 2026, 2:18 a.m.
NER Named-entity recognition batch_69a257145e0c81908a00c6c4a17b53f0 completed Feb. 28, 2026, 2:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2917de638819087f7c16d21963c63 completed Feb. 28, 2026, 6:55 a.m.
NEDg Description generation batch_69a295bbc23c81908194d6f4bea4fcd4 completed Feb. 28, 2026, 7:14 a.m.
NED2 Entity disambiguation (via description) batch_69a2968bffd881908147c66838776fef completed Feb. 28, 2026, 7:17 a.m.
Created at: Feb. 28, 2026, 2:24 a.m.