Triple
T108789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NBC |
E2196
|
entity |
| Predicate | logoDescription |
P5819
|
FINISHED |
| Object | stylized peacock with multicolored feathers |
—
|
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: stylized peacock with multicolored feathers | Statement: [NBC, logoDescription, stylized peacock with multicolored feathers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: logoDescription Context triple: [NBC, logoDescription, stylized peacock with multicolored feathers]
-
A.
logoImage
Indicates the image that serves as the logo representing an entity.
-
B.
hasLogoText
Indicates that an entity’s logo includes specific textual content or wording.
-
C.
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.
-
D.
describedIn
Indicates that information about an entity is contained or documented within a specified source, such as a text, document, or media.
-
E.
featuresText
Indicates that an entity includes or presents a specific piece of text as one of its characteristics or contents.
- 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_69a24fcdaeb48190a2d796677e4b3281 |
completed | Feb. 28, 2026, 2:15 a.m. |
| NER | Named-entity recognition | batch_69a25711f6788190a22252ea3a3af394 |
completed | Feb. 28, 2026, 2:46 a.m. |
| PD | Predicate disambiguation | batch_69a2563fd2fc819090265edbfe3092d6 |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a2570f45bc81909ebba7ee5f602976 |
completed | Feb. 28, 2026, 2:46 a.m. |
Created at: Feb. 28, 2026, 2:20 a.m.