Triple

T13417808
Position Surface form Disambiguated ID Type / Status
Subject Android 13 E313259 entity
Predicate codename P2980 FINISHED
Object Tiramisu
Tiramisu is a popular Italian layered dessert made with coffee-soaked ladyfingers, mascarpone cheese, and cocoa.
E1038278 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: Tiramisu | Statement: [Android 13, codename, Tiramisu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tiramisu
Context triple: [Android 13, codename, Tiramisu]
  • A. Cherry Garcia
    Cherry Garcia is one of Ben & Jerry’s most iconic ice cream flavors, featuring cherry ice cream with cherries and fudge flakes inspired by musician Jerry Garcia.
  • B. Dolce
    Dolce is the pet dog of Mavis Gary, the main character in the film "Young Adult."
  • C. Dolce
    Dolce is an Italian surname most famously associated with Domenico Dolce, co-founder of the luxury fashion house Dolce & Gabbana.
  • D. Macaron
    Macaron is a key supporting character in the rhythm-action game Hi-Fi Rush, known as a gentle, physically powerful ex-Vandelay employee who aids the protagonist with his engineering expertise and heavy-hitting combat support.
  • E. Vanilla Fudge
    Vanilla Fudge is an American rock band formed in the 1960s, best known for its heavy, psychedelic reworkings of contemporary pop and soul songs.
  • 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: Tiramisu
Triple: [Android 13, codename, Tiramisu]
Generated description
Tiramisu is a popular Italian layered dessert made with coffee-soaked ladyfingers, mascarpone cheese, and cocoa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tiramisu
Target entity description: Tiramisu is a popular Italian layered dessert made with coffee-soaked ladyfingers, mascarpone cheese, and cocoa.
  • A. Cherry Garcia
    Cherry Garcia is one of Ben & Jerry’s most iconic ice cream flavors, featuring cherry ice cream with cherries and fudge flakes inspired by musician Jerry Garcia.
  • B. Dolce
    Dolce is the pet dog of Mavis Gary, the main character in the film "Young Adult."
  • C. Dolce
    Dolce is an Italian surname most famously associated with Domenico Dolce, co-founder of the luxury fashion house Dolce & Gabbana.
  • D. Macaron
    Macaron is a key supporting character in the rhythm-action game Hi-Fi Rush, known as a gentle, physically powerful ex-Vandelay employee who aids the protagonist with his engineering expertise and heavy-hitting combat support.
  • E. Vanilla Fudge
    Vanilla Fudge is an American rock band formed in the 1960s, best known for its heavy, psychedelic reworkings of contemporary pop and soul songs.
  • 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_69d806ad0c44819088833ae1ec9e9690 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaeb8416c8190a00dde0917c26f51 completed April 12, 2026, 2:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69f73082a2548190aefc0f202b84165c completed May 3, 2026, 11:24 a.m.
NEDg Description generation batch_69f7311f14988190989e319741ef0ccf completed May 3, 2026, 11:27 a.m.
NED2 Entity disambiguation (via description) batch_69f731e24d508190a896875210be3189 completed May 3, 2026, 11:30 a.m.
Created at: April 9, 2026, 9:39 p.m.