Triple
T6293805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lexington Barbecue Festival |
E141081
|
entity |
| Predicate | hasApproxAttendance |
P2636
|
FINISHED |
| Object | hundreds of thousands of visitors |
—
|
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: hundreds of thousands of visitors | Statement: [Lexington Barbecue Festival, hasApproxAttendance, hundreds of thousands of visitors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasApproxAttendance Context triple: [Lexington Barbecue Festival, hasApproxAttendance, hundreds of thousands of visitors]
-
A.
attendanceAnnounced
Indicates that an official statement has been made about whether and/or how many people will attend an event.
-
B.
attendance
chosen
Indicates the relationship between an event and the people who are present at or participate in that event.
-
C.
hasAttendanceType
Indicates the specific category or mode of attendance associated with an event or participant (e.g., in-person, virtual, hybrid).
-
D.
attendanceInfluence
Indicates how one entity’s presence or participation affects the attendance level or likelihood of attendance of another entity or group.
-
E.
attendancePromotion
Indicates a relationship where one entity promotes, encourages, or incentivizes attendance at an event, activity, or location for another entity.
- 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_69c008cdf2ac8190bb640c94478fb4ed |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c06438654481908c9833c5f0d61773 |
completed | March 22, 2026, 9:50 p.m. |
| PD | Predicate disambiguation | batch_69c060df0d8881908215575862ef6831 |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:27 p.m.