Triple
T2463277
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roy Halladay |
E54582
|
entity |
| Predicate | perfectGameType |
P5812
|
FINISHED |
| Object | 20th perfect game in MLB history |
—
|
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: 20th perfect game in MLB history | Statement: [Roy Halladay, perfectGameType, 20th perfect game in MLB history]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: perfectGameType Context triple: [Roy Halladay, perfectGameType, 20th perfect game in MLB history]
-
A.
perfectGameVenue
Indicates that a perfect game was achieved at the specified venue.
-
B.
traditionalGame
Indicates that the relationship involves playing, practicing, or being associated with a game that is rooted in longstanding cultural or historical traditions.
-
C.
notableGameType
chosen
Indicates that a game is of a particular type or category for which the subject is especially well known or notable.
-
D.
competitiveGame
Indicates a relationship where entities participate in a game or contest in which they compete against each other to win or achieve a higher ranking.
-
E.
playType
Indicates the specific category or style of play or performance associated with an event or action.
- 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_69ab49dee84c819096b50a0049c347ac |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd2bc7b5481908b3664495e99f1a4 |
completed | March 7, 2026, 7:24 a.m. |
| PD | Predicate disambiguation | batch_69abd0b3ea308190a6d8499c2a542c50 |
completed | March 7, 2026, 7:16 a.m. |
Created at: March 6, 2026, 9:44 p.m.