Triple

T14304594
Position Surface form Disambiguated ID Type / Status
Subject Eltham E354659 entity
Predicate nearbyPlace P2064 FINISHED
Object Lee Green
Lee Green is a district in southeast London, England, known as a residential and commercial area within the London Borough of Lewisham.
E1091693 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: Lee Green | Statement: [Eltham, nearbyPlace, Lee Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lee Green
Context triple: [Eltham, nearbyPlace, Lee Green]
  • A. Karl Green
    Karl Green is an English bassist and singer best known as a longtime member of the 1960s pop group Herman's Hermits.
  • B. Jerry Greenfield
    Jerry Greenfield is an American businessman and philanthropist best known as the co-founder of the ice cream company Ben & Jerry's.
  • C. Jack Greene
    Jack Greene was an American country music singer best known for his 1960s and 1970s hits like "There Goes My Everything" and for his long association with the Grand Ole Opry.
  • D. Garland Greene
    Garland Greene is a notorious, eerily soft-spoken serial killer character from the action film "Con Air," portrayed by Steve Buscemi.
  • E. Jerry Scoggins
    Jerry Scoggins was an American country and western singer best known for performing the theme song to the classic television sitcom "The Beverly Hillbillies."
  • 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: Lee Green
Triple: [Eltham, nearbyPlace, Lee Green]
Generated description
Lee Green is a district in southeast London, England, known as a residential and commercial area within the London Borough of Lewisham.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lee Green
Target entity description: Lee Green is a district in southeast London, England, known as a residential and commercial area within the London Borough of Lewisham.
  • A. Karl Green
    Karl Green is an English bassist and singer best known as a longtime member of the 1960s pop group Herman's Hermits.
  • B. Jerry Greenfield
    Jerry Greenfield is an American businessman and philanthropist best known as the co-founder of the ice cream company Ben & Jerry's.
  • C. Jack Greene
    Jack Greene was an American country music singer best known for his 1960s and 1970s hits like "There Goes My Everything" and for his long association with the Grand Ole Opry.
  • D. Garland Greene
    Garland Greene is a notorious, eerily soft-spoken serial killer character from the action film "Con Air," portrayed by Steve Buscemi.
  • E. Jerry Scoggins
    Jerry Scoggins was an American country and western singer best known for performing the theme song to the classic television sitcom "The Beverly Hillbillies."
  • 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_69d8278ed42c8190b9f882dcce611347 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de85afabe48190926d6098047f4bcf completed April 14, 2026, 6:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd3d2a56a4819095b5c2164b1ad9fb completed May 8, 2026, 1:32 a.m.
NEDg Description generation batch_69fd3edf42788190b50b1144a7de41df completed May 8, 2026, 1:39 a.m.
NED2 Entity disambiguation (via description) batch_69fd3fbd931081908ba0b1838d9be49c completed May 8, 2026, 1:43 a.m.
Created at: April 10, 2026, 1:12 a.m.