Triple
T2344079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tony Romo |
E45090
|
entity |
| Predicate | becameStartingQuarterbackSeason |
P38865
|
FINISHED |
| Object | 2006 |
—
|
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: 2006 | Statement: [Tony Romo, becameStartingQuarterbackSeason, 2006]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: becameStartingQuarterbackSeason Context triple: [Tony Romo, becameStartingQuarterbackSeason, 2006]
-
A.
JetsQuarterback
Indicates that the subject is a quarterback who plays for, or is associated with, the New York Jets football team.
-
B.
playedWithQuarterback
Indicates that one player participated on the same team at the same time as a specific quarterback, sharing game or practice play together.
-
C.
notableFormerQuarterback
Indicates that the subject was previously a quarterback and is recognized as notable or distinguished in that former role.
-
D.
ColtsQuarterback
Indicates that the subject is the quarterback for the Indianapolis Colts football team.
-
E.
GreatestShowOnTurfQuarterback
Indicates that the subject is a quarterback who played for the St. Louis Rams during their high-powered offensive era commonly known as "The Greatest Show on Turf."
- 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_69a88917935081909b755dbf38e81024 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abcade3c808190ab3803538ccbe620 |
completed | March 7, 2026, 6:51 a.m. |
| PD | Predicate disambiguation | batch_69abc59616a8819099711834e6f1ccd6 |
completed | March 7, 2026, 6:28 a.m. |
| PDg | Predicate description generation | batch_69abcadd2a0c8190b6973d390e98bd66 |
completed | March 7, 2026, 6:51 a.m. |
Created at: March 4, 2026, 7:52 p.m.