Triple
T14113216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1999 AFC Championship Game |
E339696
|
entity |
| Predicate | fumblesRecoveredByTitans |
P112862
|
FINISHED |
| Object | 3 |
—
|
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: 3 | Statement: [1999 AFC Championship Game, fumblesRecoveredByTitans, 3]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fumblesRecoveredByTitans Context triple: [1999 AFC Championship Game, fumblesRecoveredByTitans, 3]
-
A.
fumbleReturnTouchdowns
Indicates the number of touchdowns a player or team scores by recovering an opponent’s fumble and returning it to the end zone.
-
B.
careerFumbleRecoveries
Indicates the total number of times an entity has recovered a fumble over the course of their entire career.
-
C.
RavensDefensiveTouchdowns
Indicates the number of touchdowns scored by the Ravens’ defense, typically by returning interceptions, fumbles, or blocked kicks for a score.
-
D.
touchdownsWithPatriots
Indicates the number of touchdowns a player scored while playing for the New England Patriots.
-
E.
interceptionReturnTouchdowns
Indicates the number of times a defensive player returns an intercepted pass into the opponent’s end zone for a touchdown.
- 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_69d81c6a95b481909e39111e0c1f31ee |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de600f992c81908133813f2894dcca |
completed | April 14, 2026, 3:41 p.m. |
| PD | Predicate disambiguation | batch_69de05b2f7e481908a9a7d40153234c0 |
completed | April 14, 2026, 9:15 a.m. |
| PDg | Predicate description generation | batch_69de2398856c81908bed6070e4ca6ab1 |
completed | April 14, 2026, 11:23 a.m. |
Created at: April 9, 2026, 10:22 p.m.