Triple
T9952543
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WLNY-TV |
E195363
|
entity |
| Predicate | hasPictureFormat |
P13218
|
FINISHED |
| Object | 1080i HDTV |
—
|
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: 1080i HDTV | Statement: [WLNY-TV, hasPictureFormat, 1080i HDTV]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPictureFormat Context triple: [WLNY-TV, hasPictureFormat, 1080i HDTV]
-
A.
typicalPictureFormat
chosen
Indicates the standard or most commonly used picture format associated with an entity (such as a device, medium, or context).
-
B.
formerPictureFormat
Indicates that an entity previously used a particular picture format before changing to a different one.
-
C.
hasFileFormat
Indicates that one entity (typically a digital file or resource) is encoded, stored, or represented using a specific file format defined by the other entity.
-
D.
hasColorFormat
Indicates that an entity uses or is associated with a specific color representation or encoding format.
-
E.
hasImageType
Indicates that an entity is associated with an image of a particular type or format.
- 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_69ca82e96a108190932bd1fc4acd73a0 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb693918081908e9f96ef302235ad |
completed | April 2, 2026, 12:21 a.m. |
| PD | Predicate disambiguation | batch_69cd1d97c44081908730071269f07712 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:46 p.m.