Triple

T27687753

Position	Surface form	Disambiguated ID	Type / Status
Subject	Innocenti	`E698076`	entity
Predicate	hadLicensingAgreementWith	`P19272`	FINISHED
Object	BMC BMC is a British motorcycle manufacturer historically known for producing small-displacement bikes and scooters, including models built under license by Innocenti.	`E1784505`	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: BMC | Statement: [Innocenti, hadLicensingAgreementWith, BMC]

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: BMC
Triple: [Innocenti, hadLicensingAgreementWith, BMC]

Generated description

BMC is a British motorcycle manufacturer historically known for producing small-displacement bikes and scooters, including models built under license by Innocenti.

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

Target predicate: hadLicensingAgreementWith
Context triple: [Innocenti, hadLicensingAgreementWith, BMC]

A. licensorOf
Indicates that one entity grants another entity permission or rights to use, produce, or distribute something under specified terms.
B. hasLicensing
Indicates that one entity holds or is granted licensing rights, permissions, or authorization in relation to another entity or resource.
C. licensePartner chosen
Indicates that one entity is authorized, via a licensing agreement, to use, distribute, or otherwise exploit another entity’s products, services, or intellectual property as a business partner.
D. rightsAgreementSignedWith
Indicates that a formal rights agreement has been executed and signed between two parties.
E. hasShareholderAgreementWith
Indicates that two or more parties are bound by a shareholder agreement governing their rights and obligations regarding shares in a company.
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_69ef590df8708190af5488f0638e790c`	completed	April 27, 2026, 12:39 p.m.
NER	Named-entity recognition	`batch_69f63574d2388190839cd1061e3c9074`	completed	May 2, 2026, 5:33 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a12dab19e148190a7265456accbb535`	completed	May 24, 2026, 11:02 a.m.
NEDg	Description generation	`batch_6a12dcb81e7c8190aff8806c7d06e8d7`	completed	May 24, 2026, 11:10 a.m.
NED2	Entity disambiguation (via description)	`batch_6a12dd3ba39481909149d5d9eb7dd5eb`	completed	May 24, 2026, 11:12 a.m.
PD	Predicate disambiguation	`batch_69f62c1a92648190835a2c5250d8c758`	completed	May 2, 2026, 4:53 p.m.

Created at: April 27, 2026, 2:50 p.m.