Triple

T1705713
Position Surface form Disambiguated ID Type / Status
Subject Linear B inscriptions E36867 entity
Predicate decipheredBy P11828 FINISHED
Object Michael Ventris
Michael Ventris was an English architect and self-taught linguist best known for deciphering the ancient Greek script Linear B, proving it encoded an early form of Greek.
E192263 NE FINISHED

How this triple was built (5 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: Michael Ventris | Statement: [Linear B inscriptions, decipheredBy, Michael Ventris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Ventris
Context triple: [Linear B inscriptions, decipheredBy, Michael Ventris]
  • A. John Desmond Bernal
    John Desmond Bernal was a pioneering Irish-born scientist who helped found the field of X-ray crystallography and made major contributions to structural biology and the social role of science.
  • B. Arthur Geoffrey Walker
    Arthur Geoffrey Walker was a British mathematician and physicist best known for his foundational contributions to relativistic cosmology, particularly the development of the Friedmann–Lemaître–Robertson–Walker (FLRW) metric.
  • C. William Wilkins
    William Wilkins was a prominent early 19th-century British architect best known for his neoclassical designs, including major public buildings and educational institutions.
  • D. Christopher Longuet-Higgins
    Christopher Longuet-Higgins was a British theoretical chemist and cognitive scientist known for his influential work in artificial intelligence and the study of human perception and cognition.
  • E. Francis Crick
    Francis Crick was a British molecular biologist best known as co-discoverer of the DNA double-helix structure, a breakthrough that transformed modern genetics and earned him a Nobel Prize.
  • 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: Michael Ventris
Triple: [Linear B inscriptions, decipheredBy, Michael Ventris]
Generated description
Michael Ventris was an English architect and self-taught linguist best known for deciphering the ancient Greek script Linear B, proving it encoded an early form of Greek.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Michael Ventris
Target entity description: Michael Ventris was an English architect and self-taught linguist best known for deciphering the ancient Greek script Linear B, proving it encoded an early form of Greek.
  • A. John Desmond Bernal
    John Desmond Bernal was a pioneering Irish-born scientist who helped found the field of X-ray crystallography and made major contributions to structural biology and the social role of science.
  • B. Arthur Geoffrey Walker
    Arthur Geoffrey Walker was a British mathematician and physicist best known for his foundational contributions to relativistic cosmology, particularly the development of the Friedmann–Lemaître–Robertson–Walker (FLRW) metric.
  • C. William Wilkins
    William Wilkins was a prominent early 19th-century British architect best known for his neoclassical designs, including major public buildings and educational institutions.
  • D. Christopher Longuet-Higgins
    Christopher Longuet-Higgins was a British theoretical chemist and cognitive scientist known for his influential work in artificial intelligence and the study of human perception and cognition.
  • E. Francis Crick
    Francis Crick was a British molecular biologist best known as co-discoverer of the DNA double-helix structure, a breakthrough that transformed modern genetics and earned him a Nobel Prize.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: decipheredBy
Context triple: [Linear B inscriptions, decipheredBy, Michael Ventris]
  • A. degreeOfDecipherment
    Indicates the extent to which something (such as a text, code, or script) has been successfully deciphered or made intelligible.
  • B. deciphermentStatus chosen
    Indicates the degree to which something (such as a text, code, or inscription) has been successfully decoded or interpreted.
  • C. decodingMethod
    Indicates the technique or process used to convert encoded or encrypted data back into its original, interpretable form.
  • D. revealedSecretOf
    Indicates that one entity has disclosed or exposed confidential or previously unknown information belonging to another entity.
  • E. declassified
    Indicates that information or material has been officially downgraded from a restricted or secret status, making it accessible to a wider audience or the public.
  • F. None of above.

Provenance (6 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_69a88617439c819094ffb5d16a0f6307 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69ab75ad24408190814069e6e3ef9e59 completed March 7, 2026, 12:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad8ad3b9c481909f83f7045789e49d completed March 8, 2026, 2:42 p.m.
NEDg Description generation batch_69ad957778a0819080f7fee35f5d8ed5 completed March 8, 2026, 3:27 p.m.
NED2 Entity disambiguation (via description) batch_69ad97aa308c81909f245a2133fc471b completed March 8, 2026, 3:37 p.m.
PD Predicate disambiguation batch_69aa61bad17c8190861b92cfb423f68f completed March 6, 2026, 5:10 a.m.
Created at: March 4, 2026, 7:30 p.m.