Triple
T28351906
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | It’s Thanksgiving |
E718119
|
entity |
| Predicate | featuresInVideo |
P80690
|
FINISHED |
| Object | Thanksgiving dinner scenes |
—
|
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: Thanksgiving dinner scenes | Statement: [It’s Thanksgiving, featuresInVideo, Thanksgiving dinner scenes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresInVideo Context triple: [It’s Thanksgiving, featuresInVideo, Thanksgiving dinner scenes]
-
A.
videoFeatures
Indicates that one entity possesses or includes specific characteristics, attributes, or elements of a video.
-
B.
featuresModelInVideo
Indicates that a video includes or showcases a particular model as part of its visual content.
-
C.
featuresIn
chosen
Indicates that an entity appears or plays a role within another entity, such as a person or element being included in a work, event, or context.
-
D.
specialFeatures
Indicates the distinctive or additional characteristics, functionalities, or attributes that set an entity apart from standard or typical versions.
-
E.
featuresDemon
Indicates that an entity includes, depicts, or prominently involves a demon.
- 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_69eff6ec27b481908c8d7b86c47893d9 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69fe6e492bf8819080b25221d13445ea |
completed | May 8, 2026, 11:14 p.m. |
| PD | Predicate disambiguation | batch_69fe6dd33a6881908fe9bbbc184cab51 |
completed | May 8, 2026, 11:12 p.m. |
Created at: April 28, 2026, 12:46 a.m.