Triple
T27687753
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Innocenti |
E698076
|
entity |
| Predicate | hadLicensingAgreementWith |
P19272
|
FINISHED |
| Object | BMC |
—
|
NE NERFINISHED |
How this triple was built (2 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]
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 (3 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. |
| PD | Predicate disambiguation | batch_69f62c1a92648190835a2c5250d8c758 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:50 p.m.