Triple
T37284477
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Don Larsen's perfect game |
E925492
|
entity |
| Predicate | rightFieldUmpire |
P188513
|
FINISHED |
| Object |
Ed Rommel
Ed Rommel was an American Major League Baseball pitcher and later umpire, best known as a pioneering knuckleballer for the Philadelphia Athletics.
|
E2220238
|
NE FINISHED |
How this triple was built (3 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: Ed Rommel | Statement: [Don Larsen's perfect game, rightFieldUmpire, Ed Rommel]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Ed Rommel Triple: [Don Larsen's perfect game, rightFieldUmpire, Ed Rommel]
Generated description
Ed Rommel was an American Major League Baseball pitcher and later umpire, best known as a pioneering knuckleballer for the Philadelphia Athletics.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rightFieldUmpire Context triple: [Don Larsen's perfect game, rightFieldUmpire, Ed Rommel]
-
A.
leftFieldUmpire
Indicates that an entity serves as the umpire positioned in the left field area relative to a particular game or play.
-
B.
startingRightFielder
Indicates that an entity serves as the right fielder in the starting lineup for a team in a particular game or context.
-
C.
leftFielder
Indicates the relationship where an entity serves in the defensive baseball position of left fielder for a team or in a specific game context.
-
D.
typeOfUmpire
Indicates the specific category or role an umpire belongs to within the broader set of umpires.
-
E.
eraAsUmpire
Indicates the time period during which an entity served in the role of an umpire.
- F. None of above. chosen
Provenance (7 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_69f76eafe20c8190856d3b996a4c31a7 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fba78aca4c8190b8f1831e8cc04e06 |
completed | May 6, 2026, 8:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a40513df2b88190b73f66b868f6f085 |
completed | June 27, 2026, 10:39 p.m. |
| NEDg | Description generation | batch_6a4051b5f6048190b92272bf19ee39ad |
completed | June 27, 2026, 10:41 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a405268e3688190b86e1ee0391e817a |
completed | June 27, 2026, 10:44 p.m. |
| PD | Predicate disambiguation | batch_69fba34a65a4819088bac6c17542d71c |
completed | May 6, 2026, 8:23 p.m. |
| PDg | Predicate description generation | batch_69fba789c1188190973a919bfe2871f3 |
completed | May 6, 2026, 8:41 p.m. |
Created at: May 3, 2026, 4:16 p.m.