Triple

T8229921
Position Surface form Disambiguated ID Type / Status
Subject Michael Ventris E192263 entity
Predicate familyName P18 FINISHED
Object Ventris
Ventris is the surname of Michael Ventris, the British architect and linguist renowned for deciphering the ancient script Linear B.
E721945 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: Ventris | Statement: [Michael Ventris, familyName, Ventris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ventris
Context triple: [Michael Ventris, familyName, Ventris]
  • A. Alticor
    Alticor is a privately held American company that serves as the corporate parent of the direct-selling giant Amway and related businesses.
  • B. Rockwell
    Rockwell is an American singer and songwriter best known for his 1984 hit single "Somebody's Watching Me."
  • C. Rockwell
    Rockwell is a Chicago Transit Authority 'L' station on the Brown Line located in the Lincoln Square neighborhood of Chicago.
  • D. Rockwell
    Rockwell is the surname of Norman Rockwell, the iconic American painter and illustrator renowned for his depictions of everyday life in the United States.
  • E. Abbott
    Abbott is a masculine given name of English origin, historically associated with clerical or religious roles.
  • 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: Ventris
Triple: [Michael Ventris, familyName, Ventris]
Generated description
Ventris is the surname of Michael Ventris, the British architect and linguist renowned for deciphering the ancient script Linear B.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ventris
Target entity description: Ventris is the surname of Michael Ventris, the British architect and linguist renowned for deciphering the ancient script Linear B.
  • A. Alticor
    Alticor is a privately held American company that serves as the corporate parent of the direct-selling giant Amway and related businesses.
  • B. Rockwell
    Rockwell is an American singer and songwriter best known for his 1984 hit single "Somebody's Watching Me."
  • C. Rockwell
    Rockwell is the surname of Norman Rockwell, the iconic American painter and illustrator renowned for his depictions of everyday life in the United States.
  • D. Rockwell
    Rockwell is a Chicago Transit Authority 'L' station on the Brown Line located in the Lincoln Square neighborhood of Chicago.
  • E. Abbott
    Abbott is a masculine given name of English origin, historically associated with clerical or religious roles.
  • 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_69ca82db5b90819085d1ad7c2e27bfcc completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7802417c81908837c31136c41a5c completed March 31, 2026, 7:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd34de56688190a7c33bbcb12cd7c1 completed April 1, 2026, 3:08 p.m.
NEDg Description generation batch_69cd4e5e9a2c819099a65053a12c8fde completed April 1, 2026, 4:57 p.m.
NED2 Entity disambiguation (via description) batch_69cd507ce2a881909da6871a9f6df119 completed April 1, 2026, 5:06 p.m.
Created at: March 30, 2026, 5:46 p.m.