Triple

T28658483

Position	Surface form	Disambiguated ID	Type / Status
Subject	Racing Métro 92	`E725397`	entity
Predicate	sponsorInName	`P15097`	FINISHED
Object	Métro Métro is a French retail and wholesale brand best known for operating cash-and-carry stores serving professional customers such as restaurants and small businesses.	`E1828903`	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: Métro | Statement: [Racing Métro 92, sponsorInName, Métro]

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: Métro
Triple: [Racing Métro 92, sponsorInName, Métro]

Generated description

Métro is a French retail and wholesale brand best known for operating cash-and-carry stores serving professional customers such as restaurants and small businesses.

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

Target predicate: sponsorInName
Context triple: [Racing Métro 92, sponsorInName, Métro]

A. sponsorshipName chosen
Indicates the name or title associated with a sponsorship relationship between entities.
B. sponsorType
Indicates the specific role or category of sponsorship that an entity provides in relation to another entity or event.
C. sponsorTo
Indicates that one entity provides support, funding, or endorsement to another entity, typically to enable or promote the latter’s activities or initiatives.
D. sponsorInHouse
Indicates that one entity formally supports, promotes, or funds another entity within the same organization, institution, or internal setting.
E. sponsorFrom
Indicates that one entity provides sponsorship or financial backing originating from a specified source entity.
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_69f01d84f5f0819087ab5e6143b14ed7`	completed	April 28, 2026, 2:37 a.m.
NER	Named-entity recognition	`batch_69f6645ba71c81908044ade6ab577018`	completed	May 2, 2026, 8:53 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a1cc39016e48190b7c5230b1d367c1c`	completed	May 31, 2026, 11:26 p.m.
NEDg	Description generation	`batch_6a1cc44ac1448190b0dc305eb5e460be`	completed	May 31, 2026, 11:29 p.m.
NED2	Entity disambiguation (via description)	`batch_6a1cc571b3b481908c523e5bad5e086a`	completed	May 31, 2026, 11:34 p.m.
PD	Predicate disambiguation	`batch_69f663362c008190a22afed262f1e426`	completed	May 2, 2026, 8:48 p.m.

Created at: April 28, 2026, 4:56 a.m.