Triple

T16463262
Position Surface form Disambiguated ID Type / Status
Subject Helaba E399863 entity
Predicate legalForm P64 FINISHED
Object Girozentrale
Girozentrale is a type of German central institution that provides banking and financial services to support and coordinate the activities of regional savings banks.
E1215258 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: Girozentrale | Statement: [Helaba, legalForm, Girozentrale]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Girozentrale
Context triple: [Helaba, legalForm, Girozentrale]
  • A. Giro
    Giro is the common shorthand name for the Giro d'Italia, one of professional cycling's three Grand Tours and Italy's premier multi-stage road race.
  • B. Schroda
    Schroda is a town in western Poland, historically part of the Prussian Province of Posen, known today as Środa Wielkopolska.
  • C. Centrum
    Centrum is the historic city center district of Amsterdam, known for its canals, landmarks, and bustling markets.
  • D. Centrum
    Centrum is the central urban district and main commercial area of the Dutch city of Meppel.
  • E. Centrum
    Centrum is the central district and main urban core of the Dutch municipality of Ridderkerk.
  • 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: Girozentrale
Triple: [Helaba, legalForm, Girozentrale]
Generated description
Girozentrale is a type of German central institution that provides banking and financial services to support and coordinate the activities of regional savings banks.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Girozentrale
Target entity description: Girozentrale is a type of German central institution that provides banking and financial services to support and coordinate the activities of regional savings banks.
  • A. Giro
    Giro is the common shorthand name for the Giro d'Italia, one of professional cycling's three Grand Tours and Italy's premier multi-stage road race.
  • B. Schroda
    Schroda is a town in western Poland, historically part of the Prussian Province of Posen, known today as Środa Wielkopolska.
  • C. Centrum
    Centrum is the historic city center district of Amsterdam, known for its canals, landmarks, and bustling markets.
  • D. Centrum
    Centrum is the central urban district and main commercial area of the Dutch city of Meppel.
  • E. Centrum
    Centrum is the central district and main urban core of the Dutch municipality of Ridderkerk.
  • 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_69d87f2dac988190b74d6e185fa88ba4 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32d824cd881909b1f2fd40e14ee35 completed April 18, 2026, 7:06 a.m.
NED1 Entity disambiguation (via context triple) batch_6a004f555f6081908b1f0d524b6fb9a7 completed May 10, 2026, 9:26 a.m.
NEDg Description generation batch_6a0050c5d4548190a674c1c19f08a9fd completed May 10, 2026, 9:32 a.m.
NED2 Entity disambiguation (via description) batch_6a0051a7ae208190b33d42cc8d4bb21f completed May 10, 2026, 9:36 a.m.
Created at: April 10, 2026, 5:10 a.m.