Triple
T3731183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcus Mariota |
E79065
|
entity |
| Predicate | playedForCollegeTeamTo |
P11550
|
FINISHED |
| Object | 2014 |
—
|
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: 2014 | Statement: [Marcus Mariota, playedForCollegeTeamTo, 2014]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: playedForCollegeTeamTo Context triple: [Marcus Mariota, playedForCollegeTeamTo, 2014]
-
A.
playedCollegeTeam
chosen
Indicates that an athlete was a member of and competed for a particular college sports team.
-
B.
playedCollegeSport
Indicates that the subject participated in an organized college-level sport for the object institution.
-
C.
positionPlayedInCollege
Indicates the specific playing position an individual held on a sports team during their college career.
-
D.
collegeTeam
Indicates that one entity is a sports team that represents or is affiliated with a particular college or university.
-
E.
workedForCollegeTeam
Indicates that an individual was employed by or served in a working role for a college sports 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.