Triple

T28553754

Position	Surface form	Disambiguated ID	Type / Status
Subject	Tunisian cuisine	`E722950`	entity
Predicate	popularDessert	`P8416`	FINISHED
Object	makroudh Makroudh is a traditional North African pastry made from semolina dough filled with dates or nuts, shaped into diamonds, and typically deep-fried and soaked in honey or syrup.	`E1823046`	NE FINISHED

How this triple was built (3 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: makroudh | Statement: [Tunisian cuisine, popularDessert, makroudh]

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: makroudh
Triple: [Tunisian cuisine, popularDessert, makroudh]

Generated description

Makroudh is a traditional North African pastry made from semolina dough filled with dates or nuts, shaped into diamonds, and typically deep-fried and soaked in honey or syrup.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: popularDessert
Context triple: [Tunisian cuisine, popularDessert, makroudh]

A. hasDessert
Indicates that one entity is served, accompanied, or associated with a particular dessert item.
B. pastryType
Indicates the specific kind or category of pastry that an item belongs to.
C. typicalFrosting
Indicates that something is the standard or commonly used type of frosting associated with a particular item or context.
D. typicalFlavor
Indicates that something characteristically has or is associated with a particular flavor.
E. traditionalSweet chosen
Indicates that something is a sweet food or dessert prepared according to long-established customs or cultural traditions.
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_69f01a60204481909af1bb76247b8221`	completed	April 28, 2026, 2:24 a.m.
NER	Named-entity recognition	`batch_69f727afd5d88190ad48735cd1b32787`	completed	May 3, 2026, 10:47 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a1cac6fa49c8190a70635026c4c34ba`	completed	May 31, 2026, 9:47 p.m.
NEDg	Description generation	`batch_6a1cade75d608190a1306aa6f0652f68`	completed	May 31, 2026, 9:53 p.m.
NED2	Entity disambiguation (via description)	`batch_6a1cae5c32f081908777415e8e460ee5`	completed	May 31, 2026, 9:55 p.m.
PD	Predicate disambiguation	`batch_69f72737c42c8190a3f781a5e98868ff`	completed	May 3, 2026, 10:45 a.m.

Created at: April 28, 2026, 3:44 a.m.