Triple
T33750655
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Live at Madison Square Garden |
E864831
|
entity |
| Predicate | recordedAtVenueCapacityCategory |
P16993
|
FINISHED |
| Object | large indoor arena |
—
|
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: large indoor arena | Statement: [Live at Madison Square Garden, recordedAtVenueCapacityCategory, large indoor arena]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recordedAtVenueCapacityCategory Context triple: [Live at Madison Square Garden, recordedAtVenueCapacityCategory, large indoor arena]
-
A.
recordedAtVenueType
Indicates that an event or recording took place at a venue of a specified type (e.g., studio, concert hall, stadium).
-
B.
audienceCapacityType
chosen
Indicates the classification or type of capacity used to describe how many audience members a venue or event space can accommodate.
-
C.
venueCapacityApproximate
Indicates an approximate or estimated capacity of a venue in terms of how many people it can accommodate.
-
D.
concertCapacity
Indicates the maximum number of people that can be accommodated at a concert event or venue.
-
E.
standingCapacity
Indicates the maximum number of people that are allowed or able to stand in a given space or vehicle.
- 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_69f3498c35f881909df279ae4270f831 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fd5d48855c8190bd93070b6a00d8b5 |
completed | May 8, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69fd5c9aabb88190912800d90184a89d |
completed | May 8, 2026, 3:46 a.m. |
Created at: May 1, 2026, 1:45 a.m.