Triple
T37159461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kodak Carousel pitch |
E920605
|
entity |
| Predicate | brandMentioned |
P45525
|
FINISHED |
| Object | Kodak |
—
|
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: Kodak | Statement: [Kodak Carousel pitch, brandMentioned, Kodak]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: brandMentioned Context triple: [Kodak Carousel pitch, brandMentioned, Kodak]
-
A.
referencesBrand
chosen
Indicates that one entity mentions, cites, or otherwise refers to a specific brand in its content or context.
-
B.
brand
Indicates that one entity is the commercial brand or label under which another entity (such as a product, service, or organization) is marketed or identified.
-
C.
mediaBrandOf
Indicates that a media outlet, channel, or publication is the brand associated with or responsible for a given piece of media content or product.
-
D.
brandIncorporatedInto
Indicates that one brand has been merged into, absorbed by, or otherwise formally integrated as part of another brand.
-
E.
brandNumber
Indicates the identifying number or code assigned to a particular brand within a system or dataset.
- 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_69f76ea0429081908c711b55599eac3c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb55de3b9c8190a7656aeab3c3ffbc |
completed | May 6, 2026, 2:53 p.m. |
| PD | Predicate disambiguation | batch_69fb35bc92e08190bff447624e2df791 |
completed | May 6, 2026, 12:36 p.m. |
Created at: May 3, 2026, 4:15 p.m.