Triple
T5239415
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Derrick Thomas |
E118301
|
entity |
| Predicate | singleGameSackRecord |
P36480
|
FINISHED |
| Object | 7 |
—
|
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: 7 | Statement: [Derrick Thomas, singleGameSackRecord, 7]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: singleGameSackRecord Context triple: [Derrick Thomas, singleGameSackRecord, 7]
-
A.
sacksByCowboysDefense
Indicates that a quarterback was sacked by the Dallas Cowboys' defensive unit.
-
B.
sackTotalNFL
Indicates the total number of quarterback sacks recorded in NFL play for the given entity.
-
C.
sacks
Indicates that one entity tackles and brings another entity to the ground, typically behind a line of scrimmage or in a way that stops their progress.
-
D.
NFLRecordHeld
chosen
Indicates that one entity holds or has held a specific NFL record associated with another entity (such as a statistic, category, or achievement).
-
E.
RavensDefensiveTouchdownPlayer
Indicates that a player on the Ravens scored a touchdown while the Ravens were on defense (e.g., via interception or fumble return).
- 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_69bd4467db0881909b3b0982df32cc8f |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7b290b88819095bc99c234260d25 |
completed | March 20, 2026, 4:51 p.m. |
| PD | Predicate disambiguation | batch_69bd77c1397c8190a7fd844d7a396e54 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:49 p.m.