Triple

T20642913
Position Surface form Disambiguated ID Type / Status
Subject Hannover Fairground E507275 entity
Predicate hasPart P35 FINISHED
Object Hermes Tower
Hermes Tower is a prominent observation and telecommunications tower located on the Hannover Fairground in Hanover, Germany.
E1442107 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: Hermes Tower | Statement: [Hannover Fairground, hasPart, Hermes Tower]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hermes Tower
Context triple: [Hannover Fairground, hasPart, Hermes Tower]
  • A. Hrelyo Tower
    Hrelyo Tower is a medieval defensive and residential tower within Bulgaria’s Rila Monastery complex, notable for its fortified architecture and historical significance.
  • B. Torre
    Torre is a neighborhood in the Brazilian city of Recife, known for its residential character and urban amenities.
  • C. Torre
    The Torre is a river in northeastern Italy that flows through the Friuli-Venezia Giulia region before joining the Isonzo River.
  • D. Torre
    Torre is a residential and commercial district within the seaside town of Torquay in Devon, England.
  • E. Torre
    Torre is the summit that marks the highest elevation in mainland Portugal, located in the Serra da Estrela mountain range.
  • 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: Hermes Tower
Triple: [Hannover Fairground, hasPart, Hermes Tower]
Generated description
Hermes Tower is a prominent observation and telecommunications tower located on the Hannover Fairground in Hanover, Germany.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hermes Tower
Target entity description: Hermes Tower is a prominent observation and telecommunications tower located on the Hannover Fairground in Hanover, Germany.
  • A. Hrelyo Tower
    Hrelyo Tower is a medieval defensive and residential tower within Bulgaria’s Rila Monastery complex, notable for its fortified architecture and historical significance.
  • B. Torre
    The Torre is a river in northeastern Italy that flows through the Friuli-Venezia Giulia region before joining the Isonzo River.
  • C. Torre
    Torre is a neighborhood in the Brazilian city of Recife, known for its residential character and urban amenities.
  • D. Torre
    Torre is the summit that marks the highest elevation in mainland Portugal, located in the Serra da Estrela mountain range.
  • E. Torre
    Torre is a surname most prominently associated with Joe Torre, the Hall of Fame Major League Baseball manager and former player.
  • 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_69e0b4be702c8190a3d2410a881d310a completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6af1c51f48190abba54a5aace9fc8 completed April 20, 2026, 10:56 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08c58cb86c81909b48e3cb231de171 completed May 16, 2026, 7:29 p.m.
NEDg Description generation batch_6a08c61afe688190bb6f755386e3df18 completed May 16, 2026, 7:31 p.m.
NED2 Entity disambiguation (via description) batch_6a08c6d846608190a1412b521b487ae7 completed May 16, 2026, 7:34 p.m.
Created at: April 16, 2026, 11:43 a.m.