Triple
T36841752
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miami Miracle |
E910426
|
entity |
| Predicate | startingYardLine |
P75604
|
FINISHED |
| Object | Miami 31-yard line |
—
|
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: Miami 31-yard line | Statement: [Miami Miracle, startingYardLine, Miami 31-yard line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startingYardLine Context triple: [Miami Miracle, startingYardLine, Miami 31-yard line]
-
A.
decidingPlayStartYardLine
Indicates the action or process of determining from which yard line a play in a game (typically football) will begin.
-
B.
interceptionYardLine
Indicates the yard line on the field where an interception occurs during a play.
-
C.
lineOfScrimmage
chosen
Indicates the position on the field where the ball is placed and play begins, separating the offensive and defensive sides before the snap.
-
D.
yardsShortOfEndZone
Indicates the number of yards separating a team or ball’s current field position from the opponent’s end zone.
-
E.
startingNoseTackle
Indicates that the subject is the primary, first-string player at the nose tackle position for a 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_69f76e7f65a881908651b702da592b6d |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a00b7fb90f881908f73edf2be8cc3a5 |
completed | May 10, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_6a00b75593d08190b3e76191cd79cdec |
completed | May 10, 2026, 4:50 p.m. |
Created at: May 3, 2026, 4:13 p.m.