Triple
T32804361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York Giants vs. Philadelphia Eagles game, December 2010 |
E838979
|
entity |
| Predicate | gameNickname |
P38618
|
FINISHED |
| Object | Miracle at the New Meadowlands |
—
|
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: Miracle at the New Meadowlands | Statement: [New York Giants vs. Philadelphia Eagles game, December 2010, gameNickname, Miracle at the New Meadowlands]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: gameNickname Context triple: [New York Giants vs. Philadelphia Eagles game, December 2010, gameNickname, Miracle at the New Meadowlands]
-
A.
notableGameNickname
chosen
Indicates that an entity is a well-known or commonly used nickname for a particular game.
-
B.
inGameName
Indicates that one entity is the name used by another entity within a specific game context.
-
C.
stageNickname
Indicates that one entity is the stage name or performance nickname used by another entity.
-
D.
decidingPlayNickname
Indicates that an entity is choosing or determining a nickname to be used for a play.
-
E.
localNickname
Indicates that an entity is known by a particular nickname within a specific local or regional context.
- 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_69f3493d35208190b4351b4e85f2fa16 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6ce6d659881909ddcec1d2966e020 |
completed | May 3, 2026, 4:26 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1667a48190b42684f6ec22dae9 |
completed | May 3, 2026, 4:16 a.m. |
Created at: May 1, 2026, 1:15 a.m.