Triple

T14476914
Position Surface form Disambiguated ID Type / Status
Subject Come and Go E358996 entity
Predicate character P662 FINISHED
Object Vi
Vi is a central character in the play "Come and Go," one of three women whose sparse, enigmatic dialogue explores themes of memory, friendship, and the passage of time.
 E1101771 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: Vi | Statement: [Come and Go, character, Vi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vi
Context triple: [Come and Go, character, Vi]
  • A. Vi
    Vi is the codename of Vi Moradi, a Resistance spy and intelligence operative in the Star Wars universe known for her missions against the First Order.
  • B. Vi
    Vi is the nickname of Violet Parr, the shy, force-field-generating teenage superhero from Pixar's "The Incredibles" films.
  • C. VI
    VI is the ISO 3166-2 code for the United States Virgin Islands, a Caribbean territory of the United States.
  • D. VI
    VI is the Roman numeral for six, used here as the designation number of the Roman legion Legio VI Victrix.
  • E. VI
    VI is the line code used to identify the Victoria line, a deep-level London Underground service running north–south across central London.
  • 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: Vi
Triple: [Come and Go, character, Vi]
Generated description
Vi is a central character in the play "Come and Go," one of three women whose sparse, enigmatic dialogue explores themes of memory, friendship, and the passage of time.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vi
Target entity description: Vi is a central character in the play "Come and Go," one of three women whose sparse, enigmatic dialogue explores themes of memory, friendship, and the passage of time.
  • A. Vi
    Vi is the codename of Vi Moradi, a Resistance spy and intelligence operative in the Star Wars universe known for her missions against the First Order.
  • B. Vi
    Vi is the nickname of Violet Parr, the shy, force-field-generating teenage superhero from Pixar's "The Incredibles" films.
  • C. VI
    VI is the ISO 3166-2 code for the United States Virgin Islands, a Caribbean territory of the United States.
  • D. VI
    VI is the Roman numeral for six, used here as the designation number of the Roman legion Legio VI Victrix.
  • E. VI
    VI is the line code used to identify the Victoria line, a deep-level London Underground service running north–south across central London.
  • 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_69d827966698819082e140837737501d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de9248edb48190a74eb032aeaac027 completed April 14, 2026, 7:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd64a0553081909fd88d8f39ed1a01 completed May 8, 2026, 4:20 a.m.
NEDg Description generation batch_69fd698579588190a49f6c7a91266117 completed May 8, 2026, 4:41 a.m.
NED2 Entity disambiguation (via description) batch_69fd6a6060488190ab5662037b52c591 completed May 8, 2026, 4:45 a.m.
Created at: April 10, 2026, 1:20 a.m.