Triple
T21895817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NFC Championship Game vs. Philadelphia Eagles on January 19, 2003 |
E540675
|
entity |
| Predicate | interceptionReturnYards |
P146084
|
FINISHED |
| Object | 92 |
—
|
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: 92 | Statement: [NFC Championship Game vs. Philadelphia Eagles on January 19, 2003, interceptionReturnYards, 92]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: interceptionReturnYards Context triple: [NFC Championship Game vs. Philadelphia Eagles on January 19, 2003, interceptionReturnYards, 92]
-
A.
interceptionReturnTouchdowns
Indicates the number of times a defensive player returns an intercepted pass into the opponent’s end zone for a touchdown.
-
B.
interceptionYardLine
Indicates the yard line on the field where an interception occurs during a play.
-
C.
interceptedQuarterback
Indicates that a defensive player successfully caught a pass thrown by the quarterback, resulting in an interception.
-
D.
careerPuntReturnYards
Indicates the total number of yards an entity has gained on punt returns over the course of their entire career.
-
E.
yardsPerReception
Indicates the average number of yards gained each time a player makes a reception.
- 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_69e0c47a95908190ae3e19b716accb3d |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f11fc6062c81908bf0aad7c6b99932 |
completed | April 28, 2026, 8:59 p.m. |
| PD | Predicate disambiguation | batch_69e6be9a65888190a66598d62d20366c |
completed | April 21, 2026, 12:02 a.m. |
| PDg | Predicate description generation | batch_69e6d054737081908aa7112975b77475 |
completed | April 21, 2026, 1:18 a.m. |
Created at: April 16, 2026, 7:07 p.m.