Triple

T32147364

Position	Surface form	Disambiguated ID	Type / Status
Subject	tarte Tatin	`E821055`	entity
Predicate	firstServedAt	`P206197`	FINISHED
Object	Hotel Tatin Hotel Tatin is the French inn historically associated with the creation of the classic upside-down caramelized apple dessert known as tarte Tatin.	`E1994227`	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: Hotel Tatin | Statement: [tarte Tatin, firstServedAt, Hotel Tatin]

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: Hotel Tatin
Triple: [tarte Tatin, firstServedAt, Hotel Tatin]

Generated description

Hotel Tatin is the French inn historically associated with the creation of the classic upside-down caramelized apple dessert known as tarte Tatin.

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

Target predicate: firstServedAt
Context triple: [tarte Tatin, firstServedAt, Hotel Tatin]

A. servedTimeAt
Indicates the specific time period during which an entity was served or received service at a particular place or context.
B. firstTakenAt
Indicates the time or date at which something was initially taken, captured, or recorded for the first time.
C. laterServedIn
Indicates that one entity subsequently held a service position or role in which another entity had previously served.
D. servedTimeFor
Indicates that one entity has completed or spent a specified duration of time serving a sentence, obligation, or term on behalf of another entity or for a particular case or offense.
E. firstServeRule
Indicates the rule or condition that determines which participant or side serves first in a game or match.
F. None of above. chosen

Provenance (7 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_69f3490520d081909b2f1271dab75faa`	completed	April 30, 2026, 12:20 p.m.
NER	Named-entity recognition	`batch_6a037c9141dc819098d7fcc36e69882c`	completed	May 12, 2026, 7:16 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a2f014463f88190b2c663aedc6ac666`	completed	June 14, 2026, 7:30 p.m.
NEDg	Description generation	`batch_6a2f0554eb7c819090a9ba44a57ff4c9`	completed	June 14, 2026, 7:47 p.m.
NED2	Entity disambiguation (via description)	`batch_6a2f05eeeb808190ad316b4eb5eb6405`	completed	June 14, 2026, 7:50 p.m.
PD	Predicate disambiguation	`batch_6a0379eaa540819095a1c5d9f3513f9b`	completed	May 12, 2026, 7:05 p.m.
PDg	Predicate description generation	`batch_6a037c7fb9f88190b384b1b68200aef0`	completed	May 12, 2026, 7:16 p.m.

Created at: May 1, 2026, 12:31 a.m.