Triple
T20082372
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mickey Guyton |
E500032
|
entity |
| Predicate | performedSongAtEvent |
P11145
|
FINISHED |
| Object | The Star-Spangled Banner at Super Bowl LVI |
—
|
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: The Star-Spangled Banner at Super Bowl LVI | Statement: [Mickey Guyton, performedSongAtEvent, The Star-Spangled Banner at Super Bowl LVI]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: performedSongAtEvent Context triple: [Mickey Guyton, performedSongAtEvent, The Star-Spangled Banner at Super Bowl LVI]
-
A.
performedSongFor
Indicates that one entity performed a song specifically for another entity as the intended audience or recipient.
-
B.
performedSong
chosen
Indicates that an entity (such as an artist or performer) has given a performance of a particular song.
-
C.
performsSongWith
Indicates that two or more entities jointly perform or present a song together.
-
D.
performedSongsBy
Indicates that one entity has performed songs that were created, owned, or associated with another entity.
-
E.
performedByAtEvent
Indicates that an action or performance was carried out by a specific agent during a particular event.
- 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_69da627770948190997f486f9a2e370f |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e665588a9c8190886b693b13a215a8 |
completed | April 20, 2026, 5:41 p.m. |
| PD | Predicate disambiguation | batch_69e54cf369b88190931532420517dac7 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:41 p.m.