Triple
T23325110
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rockefeller Center Christmas Tree |
E591267
|
entity |
| Predicate | lightingCeremonyHeldIn |
P2731
|
FINISHED |
| Object | late November or early December |
—
|
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: late November or early December | Statement: [Rockefeller Center Christmas Tree, lightingCeremonyHeldIn, late November or early December]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lightingCeremonyHeldIn Context triple: [Rockefeller Center Christmas Tree, lightingCeremonyHeldIn, late November or early December]
-
A.
ceremonyHeld
Indicates that a formal ceremony or ritual event has taken place at a particular time and/or location.
-
B.
ceremonyHeldOn
chosen
Indicates that a specific ceremony took place on a particular date or day.
-
C.
ceremonyHeldNear
Indicates that a ceremony takes place at a location that is geographically close to a specified reference place or object.
-
D.
ceremonyLocation
Indicates the place where a ceremony is held or takes place.
-
E.
lightingInauguration
Indicates the event or action of formally turning on or unveiling lighting (such as for a building, monument, or installation) in an inaugural or ceremonial context.
- 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.