Triple

T296109
Position Surface form Disambiguated ID Type / Status
Subject Max Martini E6095 entity
Predicate familyName P18 FINISHED
Object Martini
Martini is a common Italian surname shared by various notable individuals in fields such as acting, sports, and politics.
E38874 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: Martini | Statement: [Max Martini, familyName, Martini]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martini
Context triple: [Max Martini, familyName, Martini]
  • A. pisco sour
    Pisco sour is a classic South American cocktail made with pisco, citrus juice, sweetener, and egg white, renowned as a cultural icon of Peru.
  • B. Champagne
    Champagne is a renowned wine-producing region in northeastern France famous for its sparkling wines made primarily from Chardonnay, Pinot Noir, and Pinot Meunier grapes.
  • C. Brandy
    Brandy is an American R&B singer, songwriter, and actress known for her distinctive vocal style and hits such as "The Boy Is Mine" and "Have You Ever?".
  • D. Rum
    Rum is a rugged, sparsely populated island in the Inner Hebrides of Scotland, known for its dramatic mountain scenery, wildlife, and status as a National Nature Reserve.
  • E. Mocha
    Mocha is a popular JavaScript test framework used primarily for running unit and integration tests in Node.js and browser-based applications.
  • 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: Martini
Triple: [Max Martini, familyName, Martini]
Generated description
Martini is a common Italian surname shared by various notable individuals in fields such as acting, sports, and politics.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Martini
Target entity description: Martini is a common Italian surname shared by various notable individuals in fields such as acting, sports, and politics.
  • A. pisco sour
    Pisco sour is a classic South American cocktail made with pisco, citrus juice, sweetener, and egg white, renowned as a cultural icon of Peru.
  • B. Champagne
    Champagne is a renowned wine-producing region in northeastern France famous for its sparkling wines made primarily from Chardonnay, Pinot Noir, and Pinot Meunier grapes.
  • C. Brandy
    Brandy is an American R&B singer, songwriter, and actress known for her distinctive vocal style and hits such as "The Boy Is Mine" and "Have You Ever?".
  • D. Rum
    Rum is a rugged, sparsely populated island in the Inner Hebrides of Scotland, known for its dramatic mountain scenery, wildlife, and status as a National Nature Reserve.
  • E. Mocha
    Mocha is a popular JavaScript test framework used primarily for running unit and integration tests in Node.js and browser-based applications.
  • 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_69a2e79114b081909490b3bf5a5dbb51 completed Feb. 28, 2026, 1:03 p.m.
NER Named-entity recognition batch_69a2e979663481908cf9622e59fed041 completed Feb. 28, 2026, 1:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3ab9fda4c81909358613369a6848c completed March 1, 2026, 2:59 a.m.
NEDg Description generation batch_69a3aecd6fd48190843ac6f272ca83ac completed March 1, 2026, 3:13 a.m.
NED2 Entity disambiguation (via description) batch_69a3af5293b88190929dbdce5c89bf10 completed March 1, 2026, 3:15 a.m.
Created at: Feb. 28, 2026, 1:06 p.m.