Triple
T2248532
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Super Bowl XXII |
E49561
|
entity |
| Predicate | announcer |
P7529
|
FINISHED |
| Object | Frank Gifford |
E11252
|
NE 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: Frank Gifford | Statement: [Super Bowl XXII, announcer, Frank Gifford]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frank Gifford Context triple: [Super Bowl XXII, announcer, Frank Gifford]
-
A.
Frank Gifford
chosen
Frank Gifford was an American football star of the 1950s and 1960s who became a prominent sportscaster after his playing career.
-
B.
Joe Garagiola
Joe Garagiola was an American Major League Baseball catcher who became a widely recognized sportscaster and television personality.
-
C.
Walt Bellamy
Walt Bellamy was an American Hall of Fame center and Olympic gold medalist who became one of the NBA’s dominant scorers and rebounders during the 1960s.
-
D.
Morris Berg
Morris "Moe" Berg was an American Major League Baseball catcher who later became a World War II spy for the U.S. Office of Strategic Services.
-
E.
Bill Rodgers
Bill Rodgers is an American long-distance runner renowned for winning multiple Boston and New York City Marathons in the 1970s.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a88aa979788190ad6500f1d8eee2fc |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc0ed5c38819080b45ea398fb59f2 |
completed | March 7, 2026, 6:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae6b1719c481909ec3ff03d2a6f3bd |
completed | March 9, 2026, 6:39 a.m. |
Created at: March 4, 2026, 7:47 p.m.