Triple
T16756155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaboom Town! |
E407209
|
entity |
| Predicate | typicalAttendanceCategory |
P57039
|
FINISHED |
| Object | tens of thousands of attendees |
—
|
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 of attendees | Statement: [Kaboom Town!, typicalAttendanceCategory, tens of thousands of attendees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalAttendanceCategory Context triple: [Kaboom Town!, typicalAttendanceCategory, tens of thousands of attendees]
-
A.
averageAttendanceCategory
chosen
Indicates the attendance range or classification into which an entity’s typical or mean attendance level falls.
-
B.
hasTypicalAttendance
Indicates the usual or characteristic number of attendees associated with an event, venue, or activity.
-
C.
hasAttendanceType
Indicates the specific category or mode of attendance associated with an event or participant (e.g., in-person, virtual, hybrid).
-
D.
enrollmentCategory
Indicates the classification or type of enrollment under which an entity is registered or participating.
-
E.
regularCategory
Indicates that a category satisfies the additional structural conditions required to be considered a “regular” category, typically involving stable image factorizations and certain pullback properties.
- 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_69d8839174188190909f190097207065 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3abe831ec8190bac05b07db6153c1 |
completed | April 18, 2026, 4:06 p.m. |
| PD | Predicate disambiguation | batch_69e319cbd79c8190a03587a61c18bec0 |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:21 a.m.