Triple
T5706603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Authentic Brands Group |
E125797
|
entity |
| Predicate | licensesTo |
P181
|
FINISHED |
| Object | retail partners |
—
|
LITERAL FINISHED |
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: retail partners | Statement: [Authentic Brands Group, licensesTo, retail partners]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: licensesTo Context triple: [Authentic Brands Group, licensesTo, retail partners]
-
A.
licenseFor
Indicates that one entity grants or holds formal permission or authorization for another entity to perform an activity, use a resource, or operate under specified conditions.
-
B.
requiresLicenseOf
Indicates that one entity must obtain or hold the license associated with another entity in order to use, access, or perform something.
-
C.
licenseStewardship
Indicates that one entity is responsible for managing, overseeing, or administering a license on behalf of another entity.
-
D.
license
chosen
Indicates that one entity has granted another entity formal permission or authorization to use, perform, or exploit something under specified terms.
-
E.
licenseBuiltIn
Indicates that a license is inherently included within or comes standard as part of another product, service, or system rather than being added separately.
- 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_69c0082d6fe48190b777fb383769e5c8 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0248751bc8190b12aaa42d1ef17e3 |
completed | March 22, 2026, 5:19 p.m. |
| PD | Predicate disambiguation | batch_69c021c2d8bc8190b947c7d1f423d2f3 |
completed | March 22, 2026, 5:07 p.m. |
Created at: March 22, 2026, 3:45 p.m.