Triple
T1149820
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Under Armour |
E23649
|
entity |
| Predicate | hasMarketingRole |
P26086
|
FINISHED |
| Object | sports sponsorships |
—
|
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: sports sponsorships | Statement: [Under Armour, hasMarketingRole, sports sponsorships]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMarketingRole Context triple: [Under Armour, hasMarketingRole, sports sponsorships]
-
A.
hasMarketingCategory
Indicates that an entity is associated with a specific marketing category or segment used for classification or targeting.
-
B.
hasContactRole
Indicates that an entity serves in a specific role or capacity as a contact for another entity.
-
C.
hasMarket
Indicates that an entity possesses, operates in, or is associated with a particular market or marketplace.
-
D.
hasCapitalRole
Indicates that an entity holds an official role, function, or status specifically associated with a capital city.
-
E.
hasGlobalRole
Indicates that an entity holds a role or permission set that applies across an entire system or domain, rather than being limited to a specific scope or context.
- F. None of above. chosen
Provenance (4 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_69a493f0d32c8190ac74bad3c87f2641 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4bd0bed00819091d71983d787a030 |
completed | March 1, 2026, 10:26 p.m. |
| PD | Predicate disambiguation | batch_69a4bb4ee3988190ac89c5ae5b10e316 |
completed | March 1, 2026, 10:18 p.m. |
| PDg | Predicate description generation | batch_69a4bd0ab5f88190bb583fc63b4cc150 |
completed | March 1, 2026, 10:26 p.m. |
Created at: March 1, 2026, 7:44 p.m.