Triple
T2800634
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | wedding of Prince Harry and Meghan Markle |
E53143
|
entity |
| Predicate | publicCrowdEstimate |
P3653
|
FINISHED |
| Object | tens of thousands in Windsor |
—
|
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: tens of thousands in Windsor | Statement: [wedding of Prince Harry and Meghan Markle, publicCrowdEstimate, tens of thousands in Windsor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: publicCrowdEstimate Context triple: [wedding of Prince Harry and Meghan Markle, publicCrowdEstimate, tens of thousands in Windsor]
-
A.
hasCrowdLevel
Indicates the degree or intensity of how crowded a place, event, or situation is.
-
B.
approximateAudienceSize
Indicates an estimated number of individuals or entities that are expected to be reached or affected in a given context.
-
C.
passengersCountApproximate
Indicates that the number of passengers involved is given as an approximate or estimated count rather than an exact figure.
-
D.
crowdWas
Indicates that a crowd possessed or exhibited a particular state, quality, or condition.
-
E.
audienceSizeApproximate
chosen
Indicates an estimated or approximate number of people in the audience for an event or content.
- 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_69ab495a90788190941b6917e1eca3a6 |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abde2ec2ac8190bd702ad3eafb6aed |
completed | March 7, 2026, 8:13 a.m. |
| PD | Predicate disambiguation | batch_69abdd059f308190853191f6ffe2bc6f |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 9:58 p.m.