Triple
T3731202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcus Mariota |
E79065
|
entity |
| Predicate | playedForTeamFrom (Las Vegas Raiders) |
P2170
|
FINISHED |
| Object | 2020 |
—
|
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: 2020 | Statement: [Marcus Mariota, playedForTeamFrom (Las Vegas Raiders), 2020]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: playedForTeamFrom (Las Vegas Raiders) Context triple: [Marcus Mariota, playedForTeamFrom (Las Vegas Raiders), 2020]
-
A.
playedFor
chosen
Indicates that one entity has been a member of or participated as a player for a particular team, organization, or group.
-
B.
playedInNFCChampionshipGameWith
Indicates that two players participated together on the same team in at least one NFC Championship Game.
-
C.
roleAtTampaBayBuccaneers
Indicates that an entity holds or held a specific role or position within the Tampa Bay Buccaneers organization.
-
D.
NFLDebutTeam
Indicates the team for which a player made their first appearance in an NFL game.
-
E.
hasFormerTeam
Indicates that an entity was previously a member of, played for, or was affiliated with a team in the past but is no longer associated with that team.
- 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_69ad8b0e4650819090ad7cef094285e8 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcb21002c81908438170ed6f6c271 |
completed | March 8, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_69adc04746588190b0dc535638f23546 |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:34 p.m.