Triple
T17320795
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York Giants won 2–1 |
E420553
|
entity |
| Predicate | decidingGameNotablePlay |
P54545
|
FINISHED |
| Object | Bobby Thomson home run |
—
|
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: Bobby Thomson home run | Statement: [New York Giants won 2–1, decidingGameNotablePlay, Bobby Thomson home run]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: decidingGameNotablePlay Context triple: [New York Giants won 2–1, decidingGameNotablePlay, Bobby Thomson home run]
-
A.
notablePlay
Indicates that a particular play is especially famous, significant, or noteworthy in relation to the entity it is associated with.
-
B.
game7NotablePlay
Indicates that a specific play is recognized as particularly significant or memorable within the context of a Game 7.
-
C.
decidingPlay
chosen
Indicates that an action or event serves as the critical play that determines the outcome of a game or contest.
-
D.
notableGameRound
Indicates that a particular game round is especially significant or noteworthy within the context of the game or competition.
-
E.
notableGameEvent
Indicates that a specific game is associated with a significant or noteworthy event in its history or 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_69d889d22b848190a4663d0b8f8f76e7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e439cf5394819089bff5f8dc2e8241 |
completed | April 19, 2026, 2:11 a.m. |
| PD | Predicate disambiguation | batch_69e3b01b9d1c8190a406dd941c9b11a1 |
completed | April 18, 2026, 4:23 p.m. |
Created at: April 10, 2026, 5:43 a.m.