Triple

T11850147
Position Surface form Disambiguated ID Type / Status
Subject Southern Cape E281885 entity
Predicate containsTown P847 FINISHED
Object George
George is a major town in South Africa’s Western Cape, known as a commercial hub and gateway to the scenic Garden Route.
E95360 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: George | Statement: [Southern Cape, containsTown, George]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George
Context triple: [Southern Cape, containsTown, George]
  • A. George
    George is the given first name of the fictional character Gob Bluth from the television series "Arrested Development."
  • B. George
    George is the middle name of William George Barker, a renowned Canadian World War I flying ace and Victoria Cross recipient.
  • C. George
    George is the given name of George Stanley, 9th Baron Strange, an English nobleman and politician of the late 15th century.
  • D. George
    George is the given name of George Carnegie, 6th Earl of Northesk, a Scottish nobleman and naval officer in the Royal Navy.
  • E. George
    George is the given name of Lord George Murray, a prominent Scottish Jacobite general during the 18th-century uprisings.
  • 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: George
Triple: [Southern Cape, containsTown, George]
Generated description
George is a major town in South Africa’s Western Cape, known as a commercial hub and gateway to the scenic Garden Route.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: George
Target entity description: George is a major town in South Africa’s Western Cape, known as a commercial hub and gateway to the scenic Garden Route.
  • A. George chosen
    George is a town in South Africa’s Western Cape province, known as a gateway to the Garden Route and for its scenic mountains and forests.
  • B. George
    George is the given first name of South African rugby union coach Kitch Christie, who led the Springboks to victory in the 1995 Rugby World Cup.
  • C. George
    George is the given name of Sir George Grey, a prominent 19th-century British colonial governor and statesman.
  • D. George
    George is the given name of George Clinton, the influential American funk musician and bandleader behind Parliament-Funkadelic.
  • E. George
    George is a male given name commonly used in English-speaking countries and borne by numerous historical figures, including kings, presidents, and cultural icons.
  • F. None of above.

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_69d6ab287ba48190a5178779fd19b9b7 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a65db52c8190a218736da17d0153 completed April 10, 2026, 7:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69f16705cc888190b84537bd3cfbe1c2 completed April 29, 2026, 2:03 a.m.
NEDg Description generation batch_69f17005c318819090e54bc64d135477 completed April 29, 2026, 2:42 a.m.
NED2 Entity disambiguation (via description) batch_69f17814de1881908973af026af5d1d1 completed April 29, 2026, 3:16 a.m.
Created at: April 8, 2026, 9:43 p.m.