Triple

T17102099
Position Surface form Disambiguated ID Type / Status
Subject Bankside 1–3 E415003 entity
Predicate hasPart P35 FINISHED
Object Bankside 3
Bankside 3 is a modern office building on London’s South Bank, forming part of the larger Bankside 1–3 commercial development near the Tate Modern.
E1253641 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: Bankside 3 | Statement: [Bankside 1–3, hasPart, Bankside 3]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bankside 3
Context triple: [Bankside 1–3, hasPart, Bankside 3]
  • A. Bankside 2
    Bankside 2 is a commercial office building on London’s South Bank, forming part of the Bankside 1–3 development near the Tate Modern.
  • B. Bankside 1
    Bankside 1 is a major office building on London’s South Bank, known as part of the prominent Bankside 1–3 commercial development near the Tate Modern.
  • C. Rampside
    Rampside is a coastal village in the Low Furness area of Cumbria, England, known for its views over Morecambe Bay and its historic lighthouse.
  • D. Brixton Lore
    Brixton Lore is a cybernetically enhanced supervillain and former MI6 agent who serves as the primary antagonist in the action film "Fast & Furious Presents: Hobbs & Shaw."
  • E. Longside
    Longside is a small village in the Buchan area of Aberdeenshire in northeast Scotland.
  • 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: Bankside 3
Triple: [Bankside 1–3, hasPart, Bankside 3]
Generated description
Bankside 3 is a modern office building on London’s South Bank, forming part of the larger Bankside 1–3 commercial development near the Tate Modern.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bankside 3
Target entity description: Bankside 3 is a modern office building on London’s South Bank, forming part of the larger Bankside 1–3 commercial development near the Tate Modern.
  • A. Bankside 2
    Bankside 2 is a commercial office building on London’s South Bank, forming part of the Bankside 1–3 development near the Tate Modern.
  • B. Bankside 1
    Bankside 1 is a major office building on London’s South Bank, known as part of the prominent Bankside 1–3 commercial development near the Tate Modern.
  • C. Rampside
    Rampside is a coastal village in the Low Furness area of Cumbria, England, known for its views over Morecambe Bay and its historic lighthouse.
  • D. Brixton Lore
    Brixton Lore is a cybernetically enhanced supervillain and former MI6 agent who serves as the primary antagonist in the action film "Fast & Furious Presents: Hobbs & Shaw."
  • E. Longside
    Longside is a small village in the Buchan area of Aberdeenshire in northeast Scotland.
  • 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_69d886cfc8e88190b05ba466edd35591 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3dc239a088190a776fe0f4361ffc7 completed April 18, 2026, 7:31 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01482766508190b2af157bf039000d completed May 11, 2026, 3:08 a.m.
NEDg Description generation batch_6a0149940ec88190bb9c1d9f37a06a69 completed May 11, 2026, 3:14 a.m.
NED2 Entity disambiguation (via description) batch_6a014a20bb2c8190bbae3009783efc00 completed May 11, 2026, 3:16 a.m.
Created at: April 10, 2026, 5:35 a.m.