Triple
T14909722
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1984 NCAA Final Four (men's basketball) |
E371227
|
entity |
| Predicate | attendanceUnit |
P116638
|
FINISHED |
| Object | spectators |
—
|
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: spectators | Statement: [1984 NCAA Final Four (men's basketball), attendanceUnit, spectators]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: attendanceUnit Context triple: [1984 NCAA Final Four (men's basketball), attendanceUnit, spectators]
-
A.
attendance
Indicates the relationship between an event and the people who are present at or participate in that event.
-
B.
attendanceAnnounced
Indicates that an official statement has been made about whether and/or how many people will attend an event.
-
C.
attendancePromotion
Indicates a relationship where one entity promotes, encourages, or incentivizes attendance at an event, activity, or location for another entity.
-
D.
attendanceIssues
Indicates that there are problems or irregularities related to an entity’s attendance, such as frequent absences, tardiness, or non-compliance with attendance expectations.
-
E.
laterAttends
Indicates that one entity attends an event or place at a time later than another referenced attendance.
- F. None of above. chosen
Provenance (4 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_69d85cc7ea3481908228b5acb7d06f12 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded61c6b9c8190a92934d49b98fe46 |
completed | April 15, 2026, 12:04 a.m. |
| PD | Predicate disambiguation | batch_69de9a4a14a88190951bb8f4c60bd37b |
completed | April 14, 2026, 7:49 p.m. |
| PDg | Predicate description generation | batch_69deb1a4d8dc8190a4c0841c20f2875f |
completed | April 14, 2026, 9:29 p.m. |
Created at: April 10, 2026, 2:26 a.m.