Triple
T36666255
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1983 NFL season |
E905272
|
entity |
| Predicate | rushingYardsLeader |
P14717
|
FINISHED |
| Object | Eric Dickerson |
—
|
NE NERFINISHED |
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: Eric Dickerson | Statement: [1983 NFL season, rushingYardsLeader, Eric Dickerson]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rushingYardsLeader Context triple: [1983 NFL season, rushingYardsLeader, Eric Dickerson]
-
A.
rushingYardsLeaderSeasons
Indicates the seasons in which a given player led a league or competition in total rushing yards.
-
B.
rushingYards
Indicates the number of yards a player gains by running the ball on rushing plays.
-
C.
rushingYardsRecord
Indicates that an entity holds or represents the record for the greatest number of rushing yards achieved in a specified context (such as a game, season, or career).
-
D.
rushingYardsWithTeam
Indicates the number of rushing yards a player gained while playing for a specific team.
-
E.
nflRushingYardsLeader
chosen
Indicates the player who gained the most rushing yards in the NFL over a specified season or time period.
- 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_69f76e6f10008190aea41746aa1b186e |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7c780ecd0819080da2a286bf91257 |
completed | May 3, 2026, 10:09 p.m. |
| PD | Predicate disambiguation | batch_69f7c4796ebc819084a0dc08505e5f14 |
completed | May 3, 2026, 9:56 p.m. |
Created at: May 3, 2026, 4:12 p.m.