Triple
T438899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princess Margaret |
E10070
|
entity |
| Predicate | weddingBroadcast |
P6348
|
FINISHED |
| Object | first royal wedding televised in Britain |
—
|
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: first royal wedding televised in Britain | Statement: [Princess Margaret, weddingBroadcast, first royal wedding televised in Britain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: weddingBroadcast Context triple: [Princess Margaret, weddingBroadcast, first royal wedding televised in Britain]
-
A.
broadcastNetwork
Indicates that one entity serves as the television or radio network that broadcasts the programming or content of another entity.
-
B.
ceremonyType
Indicates the specific kind or category of ceremony associated with an event or relationship.
-
C.
broadcastType
chosen
Indicates the specific mode or category of broadcasting used to transmit content (e.g., live, recorded, streaming, or other broadcast formats) between entities.
-
D.
eveCelebrationOn
Indicates that an event or entity is engaged in or associated with a celebration occurring on a specific date or occasion.
-
E.
languageOfCeremony
Indicates the language in which a ceremony is conducted or officially performed.
- 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_69a2e8465ef481909655c681b01e2986 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2ef283be881909444aaf257451747 |
completed | Feb. 28, 2026, 1:35 p.m. |
| PD | Predicate disambiguation | batch_69a2eddcf50c8190bfa0d1f8ee9f604a |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:11 p.m.