Triple
T38008968
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1974 UEFA Cup Final |
E948310
|
entity |
| Predicate | attendanceFirstLeg |
P2636
|
FINISHED |
| Object | 47000 |
—
|
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: 47000 | Statement: [1974 UEFA Cup Final, attendanceFirstLeg, 47000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: attendanceFirstLeg Context triple: [1974 UEFA Cup Final, attendanceFirstLeg, 47000]
-
A.
decisiveMatchAttendance
Indicates that an entity attends a match whose outcome is crucial or decisive, such as determining a championship, qualification, or elimination.
-
B.
attendanceCategory
Indicates the classification or type assigned to an entity’s attendance status within a given context or event.
-
C.
attendanceRecordMatch
Indicates that two attendance records correspond to the same underlying event, person, or time entry according to defined matching criteria.
-
D.
attendance
chosen
Indicates the relationship between an event and the people who are present at or participate in that event.
-
E.
attendanceFeature
Indicates that an entity provides or is associated with a feature or functionality related to attendance (such as tracking, managing, or recording attendance).
- 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_69f76efb4b10819092c8c2ba28ac06a8 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc995dc2481908b3bd4217f8101e7 |
completed | May 6, 2026, 11:07 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ee04f08190977b7ad70fc85896 |
completed | May 6, 2026, 11:04 p.m. |
Created at: May 3, 2026, 4:20 p.m.