Triple
T27769484
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ACC Championship 2013 |
E701700
|
entity |
| Predicate | notablePlayer_FloridaState |
P201888
|
FINISHED |
| Object | Devonta Freeman |
—
|
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: Devonta Freeman | Statement: [ACC Championship 2013, notablePlayer_FloridaState, Devonta Freeman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notablePlayer_FloridaState Context triple: [ACC Championship 2013, notablePlayer_FloridaState, Devonta Freeman]
-
A.
floridaStartingPlayer
Indicates that the specified entity is the player who starts the game or match for the Florida team.
-
B.
teamQuarterback_FloridaState
Indicates that the subject served as the quarterback for the Florida State football team.
-
C.
notableBowlParticipant
Indicates that an entity has participated in a bowl game in a way considered notable or significant.
-
D.
notableCornerback
Indicates that the subject is recognized as an especially distinguished or prominent cornerback in American football.
-
E.
notablePlayerInFinal
Indicates that a player had a significant or standout role in the final match or game of a competition.
- F. None of above. chosen
Provenance (4 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_69ef6a52fa708190934a32308d2c92dc |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_6a002f0839fc8190a874d3b0d0826d7e |
completed | May 10, 2026, 7:08 a.m. |
| PD | Predicate disambiguation | batch_6a002eae7b6481909974b321e2789b7e |
completed | May 10, 2026, 7:07 a.m. |
| PDg | Predicate description generation | batch_6a002f071de88190b1fa4f5531a6cea7 |
completed | May 10, 2026, 7:08 a.m. |
Created at: April 27, 2026, 4:33 p.m.