Triple
T6881357
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Derrick Henry |
E158803
|
entity |
| Predicate | ledNFLIn |
P2218
|
FINISHED |
| Object | rushing yards in 2019 |
—
|
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: rushing yards in 2019 | Statement: [Derrick Henry, ledNFLIn, rushing yards in 2019]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ledNFLIn Context triple: [Derrick Henry, ledNFLIn, rushing yards in 2019]
-
A.
ledLeagueIn
chosen
Indicates that an entity achieved the highest performance or total in a specified statistical category within a particular league for a given season or time period.
-
B.
ledNFLInPassingYards
Indicates that the subject was the league leader in total passing yards in the NFL for a given season.
-
C.
ledNFLInPassingTouchdowns
Indicates that the subject was the league leader in passing touchdowns in the NFL for a given season or time period.
-
D.
nflRecord
Indicates the win-loss-tie performance record a team or individual has accumulated in NFL competition.
-
E.
nflId
Indicates a unique identifier assigned to an NFL player or entity within the dataset, used to distinguish it from all others.
- 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_69c688342f6c8190ad7eea6ba262db99 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d8e798c08190b1f494a2c1445514 |
completed | March 27, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_69c6d7b53e9881909ec298daa9f1913b |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:23 p.m.