Triple
T23325120
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rockefeller Center Christmas Tree |
E591267
|
entity |
| Predicate | starTopperLighting |
P73043
|
FINISHED |
| Object | LED lights |
—
|
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: LED lights | Statement: [Rockefeller Center Christmas Tree, starTopperLighting, LED lights]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: starTopperLighting Context triple: [Rockefeller Center Christmas Tree, starTopperLighting, LED lights]
-
A.
featuresLightingBy
Indicates that something includes or showcases lighting created, provided, or designed by a specified entity.
-
B.
lightStationBuiltFor
Indicates that a light station was constructed specifically to serve, support, or be used by a particular entity or purpose.
-
C.
lightingDesignFor
Indicates a relationship where one entity is responsible for creating or specifying the lighting design used for another entity (such as a space, event, or production).
-
D.
lightingDesigner
Indicates that an entity is responsible for planning, creating, or supervising the lighting design for a production, event, or environment.
-
E.
lightType
chosen
Indicates the specific category or kind of light associated with an entity or lighting setup.
- 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_69e25d1effe4819096907f95f610dbff |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f19787ee90819083416193efaab20f |
completed | April 29, 2026, 5:30 a.m. |
| PD | Predicate disambiguation | batch_69effcf8ca2c8190887d4f4656617d21 |
completed | April 28, 2026, 12:19 a.m. |
Created at: April 17, 2026, 5:08 p.m.