Triple

T13780747
Position Surface form Disambiguated ID Type / Status
Subject ARD E331124 entity
Predicate hasPart P35 FINISHED
Object ARD-aktuell
ARD-aktuell is the central news editorial department of the German public broadcaster ARD, responsible for flagship programs such as the “Tagesschau” and “Tagesthemen.”
E1062613 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: ARD-aktuell | Statement: [ARD, hasPart, ARD-aktuell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ARD-aktuell
Context triple: [ARD, hasPart, ARD-aktuell]
  • A. AR-D
    AR-D is the ISO 3166-2 subdivision code assigned to Argentina’s San Luis Province.
  • B. DARD
    DARD is an organization focused on translating research findings into practical applications and real-world impact.
  • C. ARITC
    ARITC is a British Army organization responsible for overseeing recruitment and the initial training of new soldiers.
  • D. ARL
    ARL (Australian Rugby League) was the top-level rugby league competition in Australia during the mid-1990s, preceding the formation of the National Rugby League (NRL).
  • E. ARL
    ARL is the airport rail link service connecting central Bangkok with Suvarnabhumi International Airport.
  • 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: ARD-aktuell
Triple: [ARD, hasPart, ARD-aktuell]
Generated description
ARD-aktuell is the central news editorial department of the German public broadcaster ARD, responsible for flagship programs such as the “Tagesschau” and “Tagesthemen.”
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: ARD-aktuell
Target entity description: ARD-aktuell is the central news editorial department of the German public broadcaster ARD, responsible for flagship programs such as the “Tagesschau” and “Tagesthemen.”
  • A. AR-D
    AR-D is the ISO 3166-2 subdivision code assigned to Argentina’s San Luis Province.
  • B. DARD
    DARD is an organization focused on translating research findings into practical applications and real-world impact.
  • C. ARITC
    ARITC is a British Army organization responsible for overseeing recruitment and the initial training of new soldiers.
  • D. ARL
    ARL (Australian Rugby League) was the top-level rugby league competition in Australia during the mid-1990s, preceding the formation of the National Rugby League (NRL).
  • E. ARL
    ARL is the airport rail link service connecting central Bangkok with Suvarnabhumi International Airport.
  • 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_69d81c583b0081909e408a17db517a21 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02460a688190a27874f8d35819c7 completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b079013881908e9f5412e5dfb0b2 completed May 3, 2026, 8:30 p.m.
NEDg Description generation batch_69f7b1d9f0b481909752dca3f74a2211 completed May 3, 2026, 8:36 p.m.
NED2 Entity disambiguation (via description) batch_69f7b32db8808190a3dcdd0fe2ce368f completed May 3, 2026, 8:42 p.m.
Created at: April 9, 2026, 10:11 p.m.